Interpretable Question Answering on Knowledge Bases and Text

Sydorova, Alona; Poerner, Nina; Roth, Benjamin

doi:10.48550/arxiv.1906.10924

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In unsupervised approaches, many QA systems have relied on structured knowledge base (KB) QA. For example, several previous works have used ConceptNet (Speer et al, 2017) to keep the QA process interpretable (Khashabi et al, 2018b;Sydorova et al, 2019). However, the construction of such structured knowledge bases is expensive, and may need frequent updates.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Yadav¹,

Bethard²,

Surdeanu³

2020

Preprint

View full text Add to dashboard Cite

Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Yadav¹,

Bethard²,

Surdeanu³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Most existing works are based on generative models, where interpretability is usually achieved via a Variational AutoEncoder (VAE) [12,13,47]. To further improve interpretability, an attention mechanism [33] is integrated to most existing methods [2,22,31,34]. Although interpretability has been applied in the domains mentioned above, there are few works that aim to interpret neural conversation models [23].…”

Section: Related Workmentioning

confidence: 99%

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions

Li¹,

Li²,

Prakash³

et al. 2020

Preprint

View full text Add to dashboard Cite

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level features from two encoders, one for context and one for label respectively. To improve the interpretability in the dual encoder models, we design a novel regularization loss to minimize the mutual information between unimportant words and desired labels, in addition to the original attention method, so that important words are emphasized while unimportant words are de-emphasized. This can help not only with model interpretability, but can also further improve model accuracy. We propose an approximation method that uses a neural network to calculate the mutual information. Furthermore, by adding a residual layer between raw word embeddings and the final encoded context feature, word-level interpretability is preserved at the final prediction of the model. We compare the proposed model with existing methods for the dialogue response task on two public datasets (Persona and Ubuntu). The experiments demonstrate the effectiveness of the proposed model in terms of better Recall@1 accuracy and visualized interpretability.

show abstract

“…There exists a large number of publicly available and widely used KGs, such as Freebase (Bollacker et al, 2008), DBpedia (Auer et al, 2007), and YAGO ontology (Suchanek et al, 2007). KGs have been effectively applied in various NLP tasks such as, relation extraction (Riedel et al, 2013;, question answering (Das et al, 2017;Sydorova et al, 2019), and dialogue systems (Xu et al, 2020). However, most KGs suffer from data sparseness as many relations between entities are not explicitly represented (Min et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion

Hakami¹,

Hakami²,

Mandya³

et al. 2022

Preprint

View full text Add to dashboard Cite

Prior work on integrating text corpora with knowledge graphs (KGs) to improve Knowledge Graph Embedding (KGE) have obtained good performance for entities that co-occur in sentences in text corpora. Such sentences (textual mentions of entity-pairs) are represented as Lexicalised Dependency Paths (LDPs) between two entities. However, it is not possible to represent relations between entities that do not co-occur in a single sentence using LDPs. In this paper, we propose and evaluate several methods to address this problem, where we borrow LDPs from the entity pairs that cooccur in sentences in the corpus (i.e. with mention entity pairs) to represent entity pairs that do not co-occur in any sentence in the corpus (i.e. without mention entity pairs). We propose a supervised borrowing method, Su-perBorrow, that learns to score the suitability of an LDP to represent a without-mention entity pair using pre-trained entity embeddings and contextualised LDP representations. Experimental results show that SuperBorrow improves the link prediction performance of multiple widely-used prior KGE methods such as TransE, DistMult, ComplEx and RotatE.

show abstract

Interpretable Question Answering on Knowledge Bases and Text

Cited by 4 publications

References 0 publications

Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions

Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion

Contact Info

Product

Resources

About