Knowledge Transfer from Answer Ranking to Answer Generation

@article{Gabburo2022KnowledgeTF,
  title={Knowledge Transfer from Answer Ranking to Answer Generation},
  author={Matteo Gabburo and Rik Koncel-Kedziorski and Siddhant Garg and Luca Soldaini and Alessandro Moschitti},
  journal={ArXiv},
  year={2022},
  volume={abs/2210.12865}
}
Recent studies show that Question Answering (QA) based on Answer Sentence Selection (AS2) can be improved by generating an improved answer from the top-k ranked answer sentences (termed GenQA). This allows for synthesizing the information from multiple candidates into a concise, natural-sounding answer. However, creating large-scale supervised training data for GenQA models is very challenging. In this paper, we propose to train a GenQA model by transferring knowledge from a trained AS2 model… 

References

SHOWING 1-10 OF 51 REFERENCES

Answer Generation for Retrieval-based Question Answering Systems

This work proposes to generate answers from a set of AS2 top candidates by training a sequence to sequence transformer model to generate an answer from a candidate set.

Joint Models for Answer Verification in Question Answering Systems

The work shows that a critical step to effectively exploiting an answer set regards modeling the interrelated information between pair of answers, and builds a three-way multi-classifier, which decides if an answer supports, refutes, or is neutral with respect to another one.

TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection

The approach establishes the state of the art on two well-known benchmarks, WikiQA and TREC-QA, achieving the impressive MAP scores and confirms the positive impact of TandA in an industrial setting, using domain specific datasets subject to different types of noise.

Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering

A question-driven pointer-generator network is designed, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating answer summaries and a new large-scale CQA corpus is constructed, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization.

Exploiting Background Knowledge in Compact Answer Generation for Why-Questions

A novel neural summarizer that combines a recurrent neural network-based encoderdecoder model with stacked convolutional neural networks and was designed to effectively exploit background knowledge, in this case a set of causal relations that was extracted from a large web data archive.

A Compare-Aggregate Model with Dynamic-Clip Attention for Answer Selection

This paper proposes a novel attention mechanism named Dynamic-Clip Attention which is directly integrated into the Compare-Aggregate framework and focuses on filtering out noise in attention matrix, in order to better mine the semantic relevance of word-level vectors.

Double Retrieval and Ranking for Accurate Question Answering

A double rerank- 016 ing model, which, for each target answer, se- 017 lects the best support; and a second neu- 018 ral retrieval stage designed to encode question 019 and answer pair as the query, which shows consistent and consistent improvement of the state of the art.

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

This paper proposes three novel sentence-level transformer pre-training objectives that incorporate paragraph-level semantics within and across documents, to improve the performance of transformers for AS2, and mitigate the requirement of large labeled datasets.

Reranking for Efficient Transformer-based Answer Selection

It is shown that standard and efficient neural rerankers can be used to reduce the amount of sentence candidates fed to Transformer models without hurting Accuracy, thus improving efficiency up to four times.

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Interestingly, it is observed that the performance of this method significantly improves when increasing the number of retrieved passages, evidence that sequence-to-sequence models offers a flexible framework to efficiently aggregate and combine evidence from multiple passages.
...