Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of possible candidates, i.e., sentences, extracted from the retrieved text. In this paper, we present Passage-based Extracting Answer Sentence In-place (PEASI), a novel design for AS2 optimized for Web-scale setting, that, instead, computes such answer without processing each candidate individually. Specifically, we design a Transformer-based framework that jointly (i) reranks passages retrieved for a question and (ii) identifies a probable answer from the top passages in place. We train PEASI in a multi-task learning framework that encourages feature sharing between the components: passage reranker and passage-based answer sentence extractor. To facilitate our development, we construct a new Web-sourced large-scale QA dataset consisting of 800,000+ labeled passages/sentences for 60,000+ questions. The experiments show that our proposed design effectively outperforms the current state-of-the-art setting for AS2, i.e., a point-wise model for ranking sentences independently, by 6.51% in accuracy, from 48.86% to 55.37%. In addition, PEASI is exceptionally efficient in computing answer sentences, requiring only ~20% inferences compared to the standard setting, i.e., reranking all possible candidates. We believe the release of PEASI, both the dataset and our proposed design, can contribute to advancing the research and development in deploying question answering services at Web scale.
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text
Peking University（北京大学）
Web 2.0带来了大量用户产生的数据，这些数据揭示了一个人的思想、经验和知识，这些数据是信息抽取和知识库构建等许多任务的重要来源。然而，文本的口语化特征对当前更适应语言形式的自然语言处理技术提出了新的挑战。省略是一种常见的语言现象，特别是在口语中，当人们从语境中理解某些词时，省略了它们，这阻碍了依存句法分析的提高，而依存句法分析对于依赖句子意义的任务具有重要意义。为了促进这一领域的研究，我们发布了一个包含319个微博的中文依存关系树库，其中包含572个句子，并保留了遗漏和上下文。
University of Information Technology（信息技术大学）；Vietnam National University Ho Chi Minh City（越南胡志明市国家大学）
Question answering (QA) systems have gained explosive attention in recent years. However, QA tasks in Vietnamese do not have many datasets. Significantly, there is mostly no dataset in the medical domain. Therefore, we built a Vietnamese Healthcare Question Answering dataset (ViHealthQA), including 10,015 question-answer passage pairs for this task, in which questions from health-interested users were asked on prestigious health websites and answers from highly qualified experts. This paper proposes a two-stage QA system based on Sentence-BERT (SBERT) using multiple negatives ranking (MNR) los…
Texts obtained from web are noisy and do not necessarily follow the orthographic sentence and word boundary rules. Thus, sentence segmentation and word tokenization systems that have been developed on well-formed texts might not perform so well on unedited web texts. In this paper, we first describe the manual annotation of sentence boundaries of an Estonian web dataset and then present the evaluation results of three existing sentence segmentation and word tokenization systems on this corpus: EstNLTK, Stanza and UDPipe. While EstNLTK obtains the highest performance compared to other systems o…
Africa has a high student-to-teacher ratio which limits students' access to teachers. Consequently, students struggle to get answers to their questions. In this work, we extended Kwame, our previous AI teaching assistant, adapted it for science education, and deployed it as a web app. Kwame for Science answers questions of students based on the Integrated Science subject of the West African Senior Secondary Certificate Examination (WASSCE). Kwame for Science is a Sentence-BERT-based question-answering web app that displays 3 paragraphs as answers along with a confidence score in response to sc…
Distant supervision (DS) has been widely used to automatically construct (noisy) labeled data for relation extraction (RE). Given two entities, distant supervision exploits sentences that directly mention them for predicting their semantic relation. We refer to this strategy as 1-hop DS, which unfortunately may not work well for long-tail entities with few supporting sentences. In this paper, we introduce a new strategy named 2-hop DS to enhance distantly supervised RE, based on the observation that there exist a large number of relational tables on the Web which contain entity pairs that shar…
This article presents a neural language architecture of sentence structure in the brain, in which sentences are temporal connection paths that interconnect neural structures underlying their words. Words remain 'in-situ', hence they are always content-addressable. Arbitrary and novel sentences (with novel words) can be created with 'neural blackboards' for words and sentences. Hence, the unlimited productivity of natural language can be achieved with a 'fixed' small world like network structure. The article focuses on the neural blackboard for sentences. The architecture uses only one 'connect…
Categorical compositional distributional semantics provide a method to derive the meaning of a sentence from the meaning of its individual words: the grammatical reduction of a sentence automatically induces a linear map for composing the word vectors obtained from distributional semantics. In this paper, we extend this passage from word-to-sentence to sentence-to-discourse composition. To achieve this we introduce a notion of basic anaphoric discourses as a mid-level representation between natural language discourse formalised in terms of basic discourse representation structures (DRS); and k…
We show that margin-based bitext mining in a multilingual sentence space can be applied to monolingual corpora of billions of sentences. We are using ten snapshots of a curated common crawl corpus (Wenzek et al., 2019) totalling 32.7 billion unique sentences. Using one unified approach for 38 languages, we were able to mine 4.5 billions parallel sentences, out of which 661 million are aligned with English. 20 language pairs have more then 30 million parallel sentences, 112 more then 10 million, and most more than one million, including direct alignments between many European or Asian languages…
Improving the quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics
Dept. of Computer Science and Engineering, University of Moratuwa（moratuwa大学计算机科学与工程系）；School of Mathematical and Computational Sciences, Massey University（massey大学数学与计算科学学院）
West Greenlandic, known by native speakers as Kalaallisut, is an extremely low-resource polysynthetic language spoken by around 56,000 people in Greenland. Here, we attempt to finetune a pretrained Kalaallisut-to-English neural machine translation (NMT) system using web-crawled pseudoparallel sentences from around 30 multilingual websites. We compile a corpus of over 93,000 Kalaallisut sentences and over 140,000 Danish sentences, then use cross-lingual sentence embeddings and approximate nearest-neighbors search in an attempt to mine near-translations from these corpora. Finally, we translate …
University of California, Los Angeles（加州大学洛杉矶分校）；Amazon Alexa AI（亚马逊Alexa AI）
Answer sentence selection (AS2) modeling requires annotated data, i.e., hand-labeled question-answer pairs. We present a strategy to collect weakly supervised answers for a question based on its reference to improve AS2 modeling. Specifically, we introduce Reference-based Weak Supervision (RWS), a fully automatic large-scale data pipeline that harvests high-quality weakly-supervised answers from abundant Web data requiring only a question-reference pair as input. We study the efficacy and robustness of RWS in the setting of TANDA, a recent state-of-the-art fine-tuning approach specialized for …
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative reduction in error compared to the best previously published result on the WMT16 document alignment shared task. Our method improves downstream MT performance on web-scraped Sinhala--English documents from ParaCrawl, outperforming the document alignment method used in the most recent ParaCrawl release. It also outperforms a comparable corpora method which uses the same multilingual embeddings, demonstrating that exp…
The problem of categorizing short speech sentences according to their semantic features with high accuracy is a subject studied in natural language processing. In this study, a data set created with samples classified in 46 different categories was used. Examples consist of sentences taken from chat conversations between a company's customer representatives and the company's website visitors. The primary purpose is to automatically tag questions and requests from visitors in the most accurate way for 46 predetermined categories for use in a chat application to generate meaningful answers to th…
University of Stavanger（斯塔万格大学）；Max Planck Institute for Informatics（马克斯·普朗克信息研究所）；University of Zurich（苏黎世大学）
We present SUMO, a neural attention-based approach that learns to establish the correctness of textual claims based on evidence in the form of text documents (e.g., news articles or Web documents). SUMO further generates an extractive summary by presenting a diversified set of sentences from the documents that explain its decision on the correctness of the textual claim. Prior approaches to address the problem of fact checking and evidence extraction have relied on simple concatenation of claim and document word embeddings as an input to claim driven attention weight computation. This is done …
Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form answers collected from three datasets, ELI5, WebGPT and Natural Questions. Our main goal is to understand how humans organize information to craft complex answers. We develop an ontology of six sentence-level functional roles for long-form answers, and annotate 3.9k sentences in 640 answer paragraphs. Different answer collection methods manifest in different disco…
准确预测合适的话语联系语（然而，此外，等等）是任何旨在从较短的句子和段落中构建连贯流畅的话语的系统的关键组成部分。例如，一个对话系统可能会通过从Web上检索的不同文档中提取的段落进行采样，从而组合出一个长而信息丰富的答案。我们制定了话语连接词预测的任务，并发布了一个由话语连接词分隔的2.9M句子对的数据集。然后，我们评估了人类评分员的任务难度，将最近提出的可分解注意力（DA）模型应用于该任务，并观察到自动预测器具有比人类评分员更高的F1（32 vs. 30）。尽管如此，在特定条件下，评分者仍然优于DA模型，这表明未来还有改进的空间。
In the majority of the existing Visual Question Answering (VQA) research, the answers consist of short, often single words, as per instructions given to the annotators during dataset construction. This study envisions a VQA task for natural situations, where the answers are more likely to be sentences rather than single words. To bridge the gap between this natural VQA and existing VQA approaches, a novel unsupervised keyword extraction method is proposed. The method is based on the principle that the full-sentence answers can be decomposed into two parts: one that contains new information ans…
We present BewQA, a system specifically designed to answer a class of questions that we call Bew questions. Bew questions are related to businesses/services such as restaurants, hotels, and movie theaters; for example, "Until what time is happy hour?". These questions are challenging to answer because the answers are found in open-domain Web, are present in short sentences without surrounding context, and are dynamic since the webpage information can be updated frequently. Under these conditions, existing QA systems perform poorly. We present a practical approach, called BewQA, that can answer…
Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have properties that hinder downstream performance, including being (1) too large, (2) beset with domain-mismatched content, and (3) heavy-headed rather than heavy-tailed (excessively many duplicate search queries such as "weather"). We show that three simple strategies for selecting language modeling data can dramatically improve rare-word recognition without harming overall performance. First, to address the heavy-headedness…
