Deep Semantic Matching is a crucial component in various natural language processing applications such as question and answering (QA), where an input query is compared to each candidate question in a QA corpus in terms of relevance. Measuring similarities between a query-question pair in an open domain scenario can be challenging due to diverse word tokens in the queryquestion pair. We propose a keyword-attentive approach to improve deep semantic matching. We first leverage domain tags from a large corpus to generate a domain-enhanced keyword dictionary. Built upon BERT, we stack a keyword-attentive transformer layer to highlight the importance of keywords in the query-question pair. During model training, we propose a new negative sampling approach based on keyword coverage between the input pair. We evaluate our approach on a Chinese QA corpus using various metrics, including precision of retrieval candidates and accuracy of semantic matching. Experiments show that our approach outperforms existing strong baselines. Our approach is general and can be applied to other text matching tasks with little adaptation.
Naver Search（Naver搜索）；Seoul National University（首尔国立大学）
Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences is required but it is yet challenging. Although attention mechanism is useful to capture the semantic relationship and to properly align the elements of two sentences, previous methods of attention mechanism simply use a summation operation which does not retain original features enough. Inspired by DenseNet, a densely connected convolutional network, we pr…
The Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention in AS. The key to reach this observation lies in phrase detection, phrase representation, phrase alignment, and more importantly how to connect those aligned phrases of different matching degrees with the final classifier. Prior work (i) has limitations in phrase generation and representation, or (ii) conducts alignment at word and phrase levels by handcraf…
University of Stavanger（斯塔万格大学）；Lero, NUI Galway（爱尔兰国立高威大学莱尔软件工程研究中心）；DFKI（德国人工智能研究中心）；University of Zurich（苏黎世大学）
Measuring the congruence between two texts has several useful applications, such as detecting the prevalent deceptive and misleading news headlines on the web. Many works have proposed machine learning based solutions such as text similarity between the headline and body text to detect the incongruence. Text similarity based methods fail to perform well due to different inherent challenges such as relative length mismatch between the news headline and its body content and non-overlapping vocabulary. On the other hand, more recent works that use headline guided attention to learn a headline der…
Fudan University（复旦大学）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）；Tencent（腾讯）
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly perform text comparison by processing each word uniformly. However, a query sentence generally comprises content that calls for different levels of matching granularity. Specifically, keywords represent factual information such as action, entity, and event that should be strictly matched, while intents convey abstract concepts and ideas that can be paraphrased int…
Jožef Stefan Institute（约热夫·斯特凡研究所）；Jožef Stefan IPS（约热夫·斯特凡研究所（IPS））；Jamova 39, Ljubljana（Jamova 39, 卢布尔雅那）
Keyword extraction is the task of identifying words (or multi-word expressions) that best describe a given document and serve in news portals to link articles of similar topics. In this work we develop and evaluate our methods on four novel data sets covering less represented, morphologically-rich languages in European news media industry (Croatian, Estonian, Latvian and Russian). First, we perform evaluation of two supervised neural transformer-based methods (TNT-KID and BERT+BiLSTM CRF) and compare them to a baseline TF-IDF based unsupervised approach. Next, we show that by combining the key…
Fuzzy string matching and language classification are important tools in Natural Language Processing pipelines, this paper provides advances in both areas. We propose a fast novel approach to string tokenisation for fuzzy language matching and experimentally demonstrate an 83.6% decrease in processing time with an estimated improvement in recall of 3.1% at the cost of a 2.6% decrease in precision. This approach is able to work even where keywords are subdivided into multiple words, without needing to scan character-to-character. So far there has been little work considering using metadata to e…
University of Alberta（阿尔伯塔大学）；Mobile Internet Group, Tencent（腾讯移动互联网事业群）
A large number of deep learning models have been proposed for the text matching problem, which is at the core of various typical natural language processing (NLP) tasks. However, existing deep models are mainly designed for the semantic matching between a pair of short texts, such as paraphrase identification and question answering, and do not perform well on the task of relevance matching between short-long text pairs. This is partially due to the fact that the essential characteristics of short-long text matching have not been well considered in these deep models. More specifically, these me…
Advertising (ad for short) keyword suggestion is important for sponsored search to improve online advertising and increase search revenue. There are two common challenges in this task. First, the keyword bidding problem: hot ad keywords are very expensive for most of the advertisers because more advertisers are bidding on more popular keywords, while unpopular keywords are difficult to discover. As a result, most ads have few chances to be presented to the users. Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywo…
National Engineering Laboratory for Speech and Language Information Processing（语音及语言信息处理国家工程实验室）；University of Science and Technology of China（中国科学技术大学）
This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. Previous studies on this topic adopt prototypical networks, which calculate the embedding vector of a query instance and the prototype vector of each support set independently. In contrast, our proposed MLMAN model encodes the query instance and each support set in an interactive way by considering their matching information at both local and instance levels. The final class prototype for each support set is obtained by attentive aggregation over the representations of its support i…
Shanghai Jiao Tong University（上海交通大学）；East China Normal University（华东师范大学）
Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the…
With the rapid growth of knowledge bases (KBs), question answering over knowledge base, a.k.a. KBQA has drawn huge attention in recent years. Most of the existing KBQA methods follow so called encoder-compare framework. They map the question and the KB facts to a common embedding space, in which the similarity between the question vector and the fact vectors can be conveniently computed. This, however, inevitably loses original words interaction information. To preserve more original information, we propose an attentive recurrent neural network with similarity matrix based convolutional neural…
Key Laboratory of Computational Linguistics, Peking University, MOE（北京大学计算语言学重点实验室（教育部））
Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a novel unsupervised framework, namely reduced attentive matching network (RAMN), to compute semantic matching between two questions. Our RAMN integrates together the deep semantic representations, the shallow lexical mismatching information and the initial rank produced by an external search engine. For the first time, we propose attention autoencoders to generate semantic represen…
BUET（孟加拉国工程技术大学）；Swinburne University of Technology（斯威本科技大学）；Melbourne University（墨尔本大学）
We introduce a novel keyword-aware influential community query KICQ that finds the most influential communities from an attributed graph, where an influential community is defined as a closely connected group of vertices having some dominance over other groups of vertices with the expertise (a set of keywords) matching with the query terms (words or phrases). We first design the KICQ that facilitates users to issue an influential CS query intuitively by using a set of query terms, and predicates (AND or OR). In this context, we propose a novel word-embedding based similarity model that enables…
University of Electronic Science and Technology of China（电子科技大学）
Job search through online matching engines nowadays are very prominent and beneficial to both job seekers and employers. But the solutions of traditional engines without understanding the semantic meanings of different resumes have not kept pace with the incredible changes in machine learning techniques and computing capability. These solutions are usually driven by manual rules and predefined weights of keywords which lead to an inefficient and frustrating search experience. To this end, we present a machine learned solution with rich features and deep learning methods. Our solution includes …
Center for Data Science（数据科学中心）；New York University（纽约大学）；School of Medicine（医学院）
Twitter data has been shown broadly applicable for public health surveillance. Previous public health studies based on Twitter data have largely relied on keyword-matching or topic models for clustering relevant tweets. However, both methods suffer from the short-length of texts and unpredictable noise that naturally occurs in user-generated contexts. In response, we introduce a deep learning approach that uses hashtags as a form of supervision and learns tweet embeddings for extracting informative textual features. In this case study, we address the specific task of estimating state-level obe…
NSF Center for Big Learning, University of Florida（佛罗里达大学NSF大数据学习中心）；AI Institute, Tongdun Technology（同盾科技人工智能研究院）
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two concrete modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by l…
Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to be incorporated. In this paper, we present a document reranking approach that combines neural query-do…
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…
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；University of Science and Technology of China（中国科学技术大学）
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially BERT. Despite the effectiveness of these models, most of them treat output labels as meaningless one-hot vectors, underestimating the semantic information and guidance of relations that these labels reveal, especially for tasks with a small number of labels. To address this problem, we propose a Relation of Relation Learning Network…
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research（资讯通信研究院）
The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new word interaction layers or attention-based matching mechanisms, it seems to be a well-established fact that these components are mandatory for good performance. Unfortunately, the memory and computation cost incurred by these complex mechanisms are undesirable for practical applications. As such, this paper tackles the question of whether it is possible to achieve competitive perf…
Neural Router: Semantic Content Matching for Agentic AI
Future Computing Group, University of Oulu（奥卢大学未来计算组）；Department of Computer Science, University of Helsinki（赫尔辛基大学计算机科学系）；Department of Communication Systems, EURECOM（EURECOM通信系统部门）
