Keyword extraction has received an increasing attention as an important research topic which can lead to have advancements in diverse applications such as document context categorization, text indexing and document classification. In this paper we propose STF-IDF, a novel semantic method based on TF-IDF, for scoring word importance of informal documents in a corpus. A set of nearly four million documents from health-care social media was collected and was trained in order to draw semantic model and to find the word embeddings. Then, the features of semantic space were utilized to rearrange the original TF-IDF scores through an iterative solution so as to improve the moderate performance of this algorithm on informal texts. After testing the proposed method with 200 randomly chosen documents, our method managed to decrease the TF-IDF mean error rate by a factor of 50% and reaching the mean error of 13.7%, as opposed to 27.2% of the original TF-IDF.
The task of determining the similarity of text documents has received considerable attention in many areas such as Information Retrieval, Text Mining, Natural Language Processing (NLP) and Computational Linguistics. Transferring data to numeric vectors is a complex task where algorithms such as tokenization, stopword filtering, stemming, and weighting of terms are used. The term frequency - inverse document frequency (TF-IDF) is the most widely used term weighting method to facilitate the search for relevant documents. To improve the weighting of terms, a large number of TF-IDF extensions are …
Washington University in St. Louis（圣路易斯华盛顿大学）；University of Southern California（南加州大学）
In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polysemy. Especially when labeled data is limited (e.g. in document classification), or the text documents are short (e.g. emails or abstracts), many features are rarely observed within the training corpus. This leads to overfitting and reduced generalization accuracy. In this paper we…
With the rapid growth of Text sentiment analysis, the demand for automatic classification of electronic documents has increased by leaps and bound. The paradigm of text classification or text mining has been the subject of many research works in recent time. In this paper we propose a technique for text sentiment classification using term frequency- inverse document frequency (TF-IDF) along with Next Word Negation (NWN). We have also compared the performances of binary bag of words model, TF-IDF model and TF-IDF with next word negation (TF-IDF-NWN) model for text classification. Our proposed m…
The dynamic web has increased exponentially over the past few years with more than thousands of documents related to a subject available to the user now. Most of the web documents are unstructured and not in an organized manner and hence user facing more difficult to find relevant documents. A more useful and efficient mechanism is combining clustering with ranking, where clustering can group the similar documents in one place and ranking can be applied to each cluster for viewing the top documents at the beginning.. Besides the particular clustering algorithm, the different term weighting fun…
For many decades, BM25 and its variants have been the dominant document retrieval approach, where their two underlying features are Term Frequency (TF) and Inverse Document Frequency (IDF). The traditional approach, however, is being rapidly replaced by Neural Ranking Models (NRMs) that can exploit semantic features. In this work, we consider BERT-based NRMs and study if IDF information is present in the NRMs. This simple question is interesting because IDF has been indispensable for the traditional lexical matching, but global features like IDF are not explicitly learned by neural language mo…
Common TF-IDF variants arise as key components in the test statistic of a penalized likelihood-ratio test for word burstiness
School of Mathematical and Computational Sciences, University of Prince Edward Island（爱德华王子岛大学数学与计算科学学院）；Canadian Centre for Climate Change and Adaptation, University of Prince Edward Island（爱德华王子岛大学加拿大气候变化与适应中心）；Faculty of Sustainable Design Engineering, University of Prince Edward Island（爱德华王子岛大学可持续设计工程学院）
For bounded datasets such as the TREC Web Track (WT10g) the computation of term frequency (TF) and inverse document frequency (IDF) is not difficult. However, when the corpus is the entire web, direct IDF calculation is impossible and values must instead be estimated. Most available datasets provide values for term count (TC) meaning the number of times a certain term occurs in the entire corpus. Intuitively this value is different from document frequency (DF), the number of documents (e.g., web pages) a certain term occurs in. We conduct a comparison study between TC and DF values within the …
A Fisher's exact test justification of the TF-IDF term-weighting scheme
School of Mathematical and Computational Sciences, University of Prince Edward Island（王子爱岛大学数学与计算科学学院）；Canadian Centre for Climate Change and Adaptation, University of Prince Edward Island（加拿大气候变化与适应中心，王子爱岛大学）；Faculty of Sustainable Design Engineering, University of Prince Edward Island（可持续设计工程学院，王子爱岛大学）
Novelty detection in text streams is a challenging task that emerges in quite a few different scenarios, ranging from email thread filtering to RSS news feed recommendation on a smartphone. An efficient novelty detection algorithm can save the user a great deal of time and resources when browsing through relevant yet usually previously-seen content. Most of the recent research on detection of novel documents in text streams has been building upon either geometric distances or distributional similarities, with the former typically performing better but being much slower due to the need of compa…
Document retrieval has taken its role in almost all domains of knowledge understanding, including the legal domain. Precedent refers to a court decision that is considered as authority for deciding subsequent cases involving identical or similar facts or similar legal issues. In this work, we propose different unsupervised approaches to solve the task of identifying relevant precedents to a given query case. Our proposed approaches are using word embeddings like word2vec, doc2vec, and sent2vec, finding cosine similarity using TF-IDF, retrieving relevant documents using BM25 scores, using the p…
Query Expansion using Pseudo Relevance Feedback is a useful and a popular technique for reformulating the query. In our proposed query expansion method, we assume that relevant information can be found within a document near the central idea. The document is normally divided into sections, paragraphs and lines. The proposed method tries to extract keywords that are closer to the central theme of the document. The expansion terms are obtained by equi-frequency partition of the documents obtained from pseudo relevance feedback and by using tf-idf scores. The idf factor is calculated for number o…
The multinomial language model has been one of the most effective models of retrieval for over a decade. However, the multinomial distribution does not model one important linguistic phenomenon relating to term-dependency, that is the tendency of a term to repeat itself within a document (i.e. word burstiness). In this article, we model document generation as a random process with reinforcement (a multivariate Polya process) and develop a Dirichlet compound multinomial language model that captures word burstiness directly. We show that the new reinforced language model can be computed as effic…
There are many existing retrieval and question answering datasets. However, most of them either focus on ranked list evaluation or single-candidate question answering. This divide makes it challenging to properly evaluate approaches concerned with ranking documents and providing snippets or answers for a given query. In this work, we present FiRA: a novel dataset of Fine-Grained Relevance Annotations. We extend the ranked retrieval annotations of the Deep Learning track of TREC 2019 with passage and word level graded relevance annotations for all relevant documents. We use our newly created da…
Athens University of Economics and Business（雅典经济与商业大学）；Google AI（谷歌人工智能）
We explore several new models for document relevance ranking, building upon the Deep Relevance Matching Model (DRMM) of Guo et al. (2016). Unlike DRMM, which uses context-insensitive encodings of terms and query-document term interactions, we inject rich context-sensitive encodings throughout our models, inspired by PACRR's (Hui et al., 2017) convolutional n-gram matching features, but extended in several ways including multiple views of query and document inputs. We test our models on datasets from the BIOASQ question answering challenge (Tsatsaronis et al., 2015) and TREC ROBUST 2004 (Voorhe…
Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level relevance modeling for document retrieval to demonstrate the ability of multi-lingual BERT to transfer models of relevance across languages. Experiments on test collections in five different languages from diverse language families (Chinese, Arabic, French, Hindi, and Bengali) show that models trained with English data improve ranking quality, without any sp…
In this paper, a simple text categorization method using term-class relevance measures is proposed. Initially, text documents are processed to extract significant terms present in them. For every term extracted from a document, we compute its importance in preserving the content of a class through a novel term-weighting scheme known as Term_Class Relevance (TCR) measure proposed by Guru and Suhil (2015) [1]. In this way, for every term, its relevance for all the classes present in the corpus is computed and stored in the knowledgebase. During testing, the terms present in the test document are…
Siemens AG（西门子股份公司）；University of Munich (LMU)（慕尼黑大学（LMU））
This paper presents our system details and results of participation in the RDoC Tasks of BioNLP-OST 2019. Research Domain Criteria (RDoC) construct is a multi-dimensional and broad framework to describe mental health disorders by combining knowledge from genomics to behaviour. Non-availability of RDoC labelled dataset and tedious labelling process hinders the use of RDoC framework to reach its full potential in Biomedical research community and Healthcare industry. Therefore, Task-1 aims at retrieval and ranking of PubMed abstracts relevant to a given RDoC construct and Task-2 aims at extracti…
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for information-seeking scenarios, users often provide information on whether a document is relevant to their query in form of clicks or explicit feedback. Therefore, in this work, we explore how relevance feedback can be directly integrated into neural re-ranking models by adopting few-shot and parameter-efficient learning techniques. Specifically, we introduce a k…
With the advent of the Internet, a new era of digital information exchange has begun. Currently, the Internet encompasses more than five billion online sites and this number is exponentially increasing every day. Fundamentally, Information Retrieval (IR) is the science and practice of storing documents and retrieving information from within these documents. Mathematically, IR systems are at the core based on a feature vector model coupled with a term weighting scheme that weights terms in a document according to their significance with respect to the context in which they appear. Practically, …
In this paper, we investigate the integration of sentence position and semantic role of words in a PageRank system to build a key phrase ranking method. We present the evaluation results of our approach on three scientific articles. We show that semantic role information, when integrated with a PageRank system, can become a new lexical feature. Our approach had an overall improvement on all the data sets over the state-of-art baseline approaches.
Carnegie Mellon University（卡内基梅隆大学）；University of Waterloo（滑铁卢大学）
While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false detail…
In addition to the frequency of terms in a document collection, the distribution of terms plays an important role in determining the relevance of documents for a given search query. In this paper, term distribution analysis using Fourier series expansion as a novel approach for calculating an abstract representation of term positions in a document corpus is introduced. Based on this approach, two methods for improving the evaluation of document relevance are proposed: (a) a function-based ranking optimization representing a user defined document region, and (b) a query expansion technique base…
This paper reports the use of a document distance-based approach to automatically expand the number of available relevance judgements when these are limited and reduced to only positive judgements. This may happen, for example, when the only available judgements are extracted from a list of references in a published review paper. We compare the results on two document sets: OHSUMED, based on medical research publications, and TREC-8, based on news feeds. We show that evaluations based on these expanded relevance judgements are more reliable than those using only the initially available judgeme…
In light of the tremendous amount of data produced by social media, a large body of research have revisited the relevance estimation of the users' generated content. Most of the studies have stressed the multidimensional nature of relevance and proved the effectiveness of combining the different criteria that it embodies. Traditional relevance estimates combination methods are often based on linear combination schemes. However, despite being effective, those aggregation mechanisms are not effective in real-life applications since they heavily rely on the non-realistic independence property of …
Traditional information retrieval (IR) ranking models process the full text of documents. Newer models based on Transformers, however, would incur a high computational cost when processing long texts, so typically use only snippets from the document instead. The model's input based on a document's URL, title, and snippet (UTS) is akin to the summaries that appear on a search engine results page (SERP) to help searchers decide which result to click. This raises questions about when such summaries are sufficient for relevance estimation by the ranking model or the human assessor, and whether hum…
Personalized search provides a potentially powerful tool, however, it is limited due to the large number of roles that a person has: parent, employee, consumer, etc. We present the role-relevance algorithm: a search technique that favors search results relevant to the user's current role. The role-relevance algorithm uses three factors to score documents: (1) the number of keywords each document contains; (2) each document's geographic relevance to the user's role (if applicable); and (3) each document's topical relevance to the user's role (if applicable). Topical relevance is assessed using …
In this paper, we introduce a new measure called Term_Class relevance to compute the relevancy of a term in classifying a document into a particular class. The proposed measure estimates the degree of relevance of a given term, in placing an unlabeled document to be a member of a known class, as a product of Class_Term weight and Class_Term density; where the Class_Term weight is the ratio of the number of documents of the class containing the term to the total number of documents containing the term and the Class_Term density is the relative density of occurrence of the term in the class to t…
Research has been devoted in the past few years to relevance feedback as an effective solution to improve performance of information retrieval systems. Relevance feedback refers to an interactive process that helps to improve the retrieval performance. In this paper we propose the use of relevance feedback to improve document image retrieval System (DIRS) performance. This paper compares a variety of strategies for positive and negative feedback. In addition, feature subspace is extracted and updated during the feedback process using a Principal Component Analysis (PCA) technique and based on …
DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation
ETH Zurich（苏黎世联邦理工学院）；University of Zurich（苏黎世大学）；Swiss Finance Institute (SFI)（瑞士金融研究所）；University of Electronic Science and Technology of China（电子科技大学）
Texas A&M University（得克萨斯农工大学）；Facebook AI Research（Facebook人工智能研究院）
Existing search engines use keyword matching or tf-idf based matching to map the query to the web-documents and rank them. They also consider other factors such as page rank, hubs-and-authority scores, knowledge graphs to make the results more meaningful. However, the existing search engines fail to capture the meaning of query when it becomes large and complex. BERT, introduced by Google in 2018, provides embeddings for words as well as sentences. In this paper, I have developed a semantics-oriented search engine using neural networks and BERT embeddings that can search for query and rank the…
In the context of depth-$k$ pooling for constructing web search test collections, we compare two approaches to ordering pooled documents for relevance assessors: the prioritisation strategy (PRI) used widely at NTCIR, and the simple randomisation strategy (RND). In order to address research questions regarding PRI and RND, we have constructed and released the WWW3E8 data set, which contains eight independent relevance labels for 32,375 topic-document pairs, i.e., a total of 259,000 labels. Four of the eight relevance labels were obtained from PRI-based pools; the other four were obtained from …
As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval. Previously, an effective technique, relevance feedback (RF), has rarely been used in real search scenarios due to the overhead of collecting users' relevance judgments. However, since users tend to interact more with the search results shown on the new interfaces, it becomes feasible to obtain users' assessments on a few results during each interaction. This makes iterative relevance feedb…
Relevance judgment in Information Retrieval is influenced by multiple factors. These include not only the topicality of the documents but also other user oriented factors like trust, user interest, etc. Recent works have identified these various factors into seven dimensions of relevance. In a previous work, these relevance dimensions were quantified and user's cognitive state with respect to a document was represented as a state vector in a Hilbert Space, with each relevance dimension representing a basis. It was observed that relevance dimensions are incompatible in some documents, when maki…
Now a days, the text document is spontaneously increasing over the internet, e-mail and web pages and they are stored in the electronic database format. To arrange and browse the document it becomes difficult. To overcome such problem the document preprocessing, term selection, attribute reduction and maintaining the relationship between the important terms using background knowledge, WordNet, becomes an important parameters in data mining. In these paper the different stages are formed, firstly the document preprocessing is done by removing stop words, stemming is performed using porter stemm…
Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted a late interaction architecture with pre-computed contextual token representations at the cost of a large online storage. This paper proposes contextual quantization of token embeddings by decoupling document-specific and document-independent ranking contributions during codebook-based compression. This allows effective online decompression and embedding composition for better…
Text Categorization is traditionally done by using the term frequency and inverse document frequency.This type of method is not very good because, some words which are not so important may appear in the document .The term frequency of unimportant words may increase and document may be classified in the wrong category.For reducing the error of classifying of documents in wrong category. The Distributional features are introduced. In the Distribuional Features, the Distribution of the words in the whole document is analyzed. Whole Document is very closely analyzed for different measures like Fir…
