Challenge: Existing approaches for non-factoid question answering can be categorized into representation and interaction focused approaches.
Approach: They propose a novel approach which derives contextualized uni-gram representation from n-grams.
Outcome: The proposed approach achieves state-of-the-art in two public non-factoid question answering datasets.

Similar Papers

Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for document summarization use extractive and abstractive representations, but they don't take into account hierarchical structure of document clusters.
Approach: They propose a multi-granularity interaction network for extractive and abstractive multi-document summarization which jointly learn semantic representations for words, sentences, and documents.
Outcome: The proposed model outperforms baseline methods and achieves the best results on the Multi-News dataset.
Unsupervised Natural Question Answering with a Small Model (D19-66)

Copied to clipboard

Challenge: a recent demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is embedded directly within these large models.
Approach: They propose to use unsupervised learning techniques to add knowledge explicitly without extensive training.
Outcome: The proposed architecture allows for explicit addition of knowledge without extensive training.
Contextualized Word Representations for Reading Comprehension (N18-2)

Copied to clipboard

Challenge: Reading comprehension (RC) is a high-level task in natural language understanding that requires reading a document and answering questions about its content.
Approach: They propose to provide a standard neural network for reading a document and answering a question about its content.
Outcome: The proposed model improves on the competitive SQuAD dataset by providing rich contextualized word representations and allowing it to choose between context-dependent and context-independent representations.
Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods for Knowledge Base Question Answering rely on semantic parsing and information retrieval.
Approach: They propose a contrastive regularization based method to extract correct answer entities from a context knowledge base and a corresponding question.
Outcome: The proposed method achieves state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.
Alignment over Heterogeneous Embeddings for Question Answering (N19-1)

Copied to clipboard

Challenge: Existing approaches for non-factoid question answering are based on heterogeneous embeddings that model text at different levels of abstraction.
Approach: They propose a fast, mostly-unsupervised approach for non-factoid question answering called Alignment over Heterogeneous Embeddings (AHE) it aligns each word in the question and candidate answer with the most similar word in retrieved supporting paragraph and a meta-classifier that learns how much to trust the predictions over each representation.
Outcome: The proposed approach outperforms other supervised approaches on the AI2 Reasoning Challenge dataset and the WikiQA dataset.
NLQuAD: A Non-Factoid Long Question Answering Data Set (2021.eacl-main)

Copied to clipboard

Challenge: Existing data sets for document-level question answering are limited in their ability to detect short text and require multiple-sentence descriptive answers and opinions.
Approach: They introduce a new data set with baseline methods for non-factoid long question answering . they compare BERT, RoBERTa, and Longformer models to establish baseline performances .
Outcome: Experimental results show that Longformer outperforms the other architectures but human evaluations show that it is far behind the human upper bound.
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering (P18-1)

Copied to clipboard

Challenge: Existing approaches to read comprehension style question answering are limited by the volume of annotated datasets.
Approach: They propose a hierarchical attention network for reading comprehension style question answering . they first encode the question and paragraph with fine-grained language embeddings . then propose fusion approach to fuse information from both global and attended representations based on the hierarchic attention network .
Outcome: The proposed method achieves state-of-the-art on the SQuAD and TriviaQA Wiki leaderboards and two adversarial SQu AD datasets.
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing question answering datasets focus on dealing with homogeneous information, but using homogenous information alone might lead to coverage problems.
Approach: They propose a large-scale question-answering dataset that requires reasoning on heterogeneous information.
Outcome: The proposed model can achieve an EM score of 40% while the existing model is far behind human performance.
Knowledge Base Question Answering via Encoding of Complex Query Graphs (D18-1)

Copied to clipboard

Challenge: Existing KBQA methods focus on simpler questions and do not work well on complex questions . a knowledge-based question answering approach is able to answer complex questions using a standard knowledge base .
Approach: They propose to encode query structure into a uniform vector representation of a question and its semantic components into .
Outcome: The proposed approach outperforms existing methods on complex questions while staying competitive on simple questions.
Context-Aware Interaction Network for Question Matching (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models focus on word-level local matching and neglect the importance of contextual information.
Approach: They propose a context-aware interaction network to properly align two sequences and infer their semantic relationship by using gate fusion layers.
Outcome: The proposed model can accurately align two sequences and infer their semantic relationship on two question matching datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations