Composing Answer from Multi-spans for Reading Comprehension
- URL: http://arxiv.org/abs/2009.06141v2
- Date: Mon, 23 Aug 2021 14:56:36 GMT
- Title: Composing Answer from Multi-spans for Reading Comprehension
- Authors: Zhuosheng Zhang, Yiqing Zhang, Hai Zhao, Xi Zhou, Xiang Zhou
- Abstract summary: We present a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks.
The proposed method has a better performance on accurately generating long answers, and substantially outperforms two competitive typical one-span and Seq2Seq baseline decoders.
- Score: 77.32873012668783
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents a novel method to generate answers for non-extraction
machine reading comprehension (MRC) tasks whose answers cannot be simply
extracted as one span from the given passages. Using a pointer network-style
extractive decoder for such type of MRC may result in unsatisfactory
performance when the ground-truth answers are given by human annotators or
highly re-paraphrased from parts of the passages. On the other hand, using
generative decoder cannot well guarantee the resulted answers with well-formed
syntax and semantics when encountering long sentences. Therefore, to alleviate
the obvious drawbacks of both sides, we propose an answer making-up method from
extracted multi-spans that are learned by our model as highly confident
$n$-gram candidates in the given passage. That is, the returned answers are
composed of discontinuous multi-spans but not just one consecutive span in the
given passages anymore. The proposed method is simple but effective: empirical
experiments on MS MARCO show that the proposed method has a better performance
on accurately generating long answers, and substantially outperforms two
competitive typical one-span and Seq2Seq baseline decoders.
Related papers
- FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection [61.9638234358049]
FastFiD is a novel approach that executes sentence selection on encoded passages.
This aids in retaining valuable sentences while reducing the context length required for generating answers.
arXiv Detail & Related papers (2024-08-12T17:50:02Z) - Self-Consistent Decoding for More Factual Open Responses [28.184313177333642]
"Sample & Select" improves factuality by a 30% relative margin against decoders of DoLA, P-CRR, and S-CRR.
We collect human verifications of the generated summaries, confirming the factual superiority of our method.
arXiv Detail & Related papers (2024-03-01T17:31:09Z) - To Answer or Not to Answer? Improving Machine Reading Comprehension
Model with Span-based Contrastive Learning [9.490758388465697]
We propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts at the answer span level.
Experiments on SQuAD 2.0 dataset show that spanCL can improve baselines significantly, yielding 0.86-2.14 absolute EM improvements.
arXiv Detail & Related papers (2022-08-02T08:09:05Z) - Predict and Use Latent Patterns for Short-Text Conversation [5.757975605648179]
We propose to use more detailed semantic forms, including latent responses and part-of-speech sequences, as the controllable semantics to guide the generation.
Our results show that the richer semantics are not only able to provide informative and diverse responses, but also increase the overall performance of response quality.
arXiv Detail & Related papers (2020-10-27T01:31:42Z) - Multi-span Style Extraction for Generative Reading Comprehension [90.6069071495214]
We propose a new framework which enables generative MRC to be smoothly solved as multi-span extraction.
Thorough experiments demonstrate that this novel approach can alleviate the dilemma between generative models and single-span models.
arXiv Detail & Related papers (2020-09-15T23:06:48Z) - Recurrent Chunking Mechanisms for Long-Text Machine Reading
Comprehension [59.80926970481975]
We study machine reading comprehension (MRC) on long texts.
A model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer.
We propose to let a model learn to chunk in a more flexible way via reinforcement learning.
arXiv Detail & Related papers (2020-05-16T18:08:58Z) - Document Modeling with Graph Attention Networks for Multi-grained
Machine Reading Comprehension [127.3341842928421]
Natural Questions is a new challenging machine reading comprehension benchmark.
It has two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer)
Existing methods treat these two sub-tasks individually during training while ignoring their dependencies.
We present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature.
arXiv Detail & Related papers (2020-05-12T14:20:09Z) - Answer Generation through Unified Memories over Multiple Passages [10.965065178451104]
Our method is called neural answer Generation through Unified Memories over Multiple Passages (GUM-MP)
First, it determines which tokens in the passages are matched to the question.
In particular, it investigates matches between tokens in positive passages, which are assigned to the question, and those in negative passages, which are not related to the question.
Finally, it encodes the token sequences with the above two matching results into unified memories in the passage encoders and learns the answer sequence by using an encoder-decoder with a multiple-pointer-generator mechanism.
arXiv Detail & Related papers (2020-04-22T11:46:40Z) - Retrospective Reader for Machine Reading Comprehension [90.6069071495214]
Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage.
When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder.
This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions.
arXiv Detail & Related papers (2020-01-27T11:14:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.