Learning to Paraphrase for Question Answering

By Li Dong, Jonathan Mallinson, Siva Reddy, Mirella Lapata. 2017

225 citations recorded by the source corpus.

Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need. In this paper we turn to paraphrases as a means of capturing this knowledge and present a general framework which learns felicitous paraphrases for various QA tasks. Our method is trained end-to-end using question-answer pairs as a supervision signal. A question and its paraphrases serve as input to a neural scoring model which assigns higher weights to linguistic expressions most likely to yield correct answers. We evaluate our approach on QA over Freebase and answer sentence selection. Experimental results on three datasets show that our framework consistently improves performance, achieving competitive results despite the use of simple QA models.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension (2018, methodology): “It is worth to note that (Dong et al., 2017) use paraphrasing techniques to improve QA; however, they only paraphrase questions and did not focus on the data augmentation aspect as we do in this paper.”
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (2019, methodology): “Some works have directly used QG in QA models’ pipeline (Duan et al., 2017; Dong et al., 2017; Lewis and Fan, 2019).”
Adversarial Example Generation with Syntactically Controlled Paraphrase Networks (2018, methodology): “Li et al. (2017) generate paraphrases using deep reinforcement learning.”
Style Transfer Through Back-Translation (2018, methodology): “Our work is also closely-related to a problem of paraphrase generation (Madnani and Dorr, 2010; Dong et al., 2017), including methods relying on (phrase-based) back-translation (Ganitkevitch et al.”
Grounded Adaptation for Zero-shot Executable Semantic Parsing (2020, background): “Dong et al. (2017) and Yu et al. (2018a) respectively paraphrase and back-translate (Sennrich et al., 2016; Edunov et al., 2018) questions and documents to improve question-answering.”
ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters (2018, background): “Past work has demonstrated the bene-ﬁts of paraphrasing for QA (Abujabal et al., 2018; Berant and Liang, 2014; Dong et al., 2017; Fader et al., 2013).”
Learning Out-of-Vocabulary Words in Intelligent Personal Agents (2018, methodology): “) we add this example to T 0 and retrain P para : Using paraphrases to improve NLP systems have been studied recently e.g. in QA [ Dong et al. , 2017 ] , semantic parsing [Berant and Liang, 2014].”
Can You Unpack That? Learning to Rewrite Questions-in-Context (2019, background): “els that simplify hard questions through paraphrasing (Dong et al., 2017) or decomposition (Talmor and Berant, 2018).”
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (2018, methodology): “For this problem, we can employ sentence rewriting or paraphrasing techniques (Chen et al., 2016; Dong et al., 2017) to transform unseen sentence structures into normal ones.”
Learning an Executable Neural Semantic Parser (2017, unknown): “al. 2013b) 10.8 PARASEMPRE (Berant and Liang 2014) 12.8 JACANA (Yao and Van Durme 2014) 5.1 SIMPLEGRAPH (Reddy et al. 2016) 15.9 UDEPLAMBDA (Reddy et al. 2017) 17.6 Sequence-to-sequence 16.2 PARA4QA (Dong et al. 2017) 20.4 TNSP with soft attention, top down 17.3 TNSP with hard attention, top down 16”
Improving the Robustness of Question Answering Systems to Question Paraphrasing (2019, unknown): “Dong et al. (2017) ﬁrst generated multiple para-phrases for a given question and used a neural network to score the quality of each paraphrase.”
Answering Science Exam Questions Using Query Rewriting with Background Knowledge (2018, methodology): “, 2013) and machine translation techniques (Dong et al., 2017) have performed well for both structured query generation and answer selection.”
Paraphrase Generation: A Survey of the State of the Art (2021, background): “Paraphrasing can be play an important role in language understanding tasks, such as question answering (Dong et al., 2017; Zhu et al., 2017), machine translation (Seraj et al., 2015; Thompson and Post, 2020a), and semantic parsing (Berant and Liang, 2014; Cao et al., 2020).”
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018, background): “There also has been inference or entailment work that is more generation focused: generating, e.g., entailed statements (Zhang et al., 2017; Blouw and Eliasmith, 2018), explanations of causality (Kang et al., 2017), or paraphrases (Dong et al., 2017).”
Focus Attention: Promoting Faithfulness and Diversity in Summarization (2021, background): “For conditional text generation, most work focuses on generating diverse questions (Narayan et al., 2016; Dong et al., 2017; Sultan et al., 2020; Wang et al., 2020b) or paraphrases (Li et al., 2016b; Dai et al., 2017; Xu et al., 2018; Cao and Wan, 2020).”
Unsupervised Paraphrase Generation using Pre-trained Language Models (2020, background): “Paraphrasing has also been explored as a means to improve Question answering in [9] and [10] by making the training more robust by incorporating reformulations.”
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering (2019, methodology): “Dong et al. (2017) tackle QA by marginalizing the probability of an answer over a set of paraphrases, generated using rule-based and NMT-based methods.”
Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue (2019, background): “Other work in generation addresses tasks such as rephrasals for generating paraphrases (Prakash et al., 2016; Gupta et al., 2018), sentence simpliﬁ-cation (Narayan et al., 2017), and query rewriting for question answering (Dong et al., 2017).”
Controllable Paraphrase Generation with a Syntactic Exemplar (2019, background): “We focus primarily on the task of paraphrase generation, which has received significant recent attention (Quirk et al., 2004; Prakash et al., 2016; Mallinson et al., 2017; Dong et al., 2017; Ma et al., 2018; Li et al., 2018).”
Learning to Collaborate for Question Answering and Asking (2018, methodology): “The approach of (Dong et al., 2017) learns to generate question from question via paraphrasing, and use the generated questions in the inference process.”