TY - GEN
T1 - A STEP towards Interpretable Multi-Hop Reasoning
T2 - 13th International Conference on Language Resources and Evaluation Conference, LREC 2022
AU - Luo, Fan
AU - Surdeanu, Mihai
N1 - Funding Information:
This work was partially supported by the Defense Advanced Research Projects Agency (DARPA) under the World Modelers program, grant number W911NF1810014. Mihai Surdeanu declares a financial interest in lum.ai. This interest has been properly disclosed to the University of Arizona Institutional Review Committee and is managed in accordance with its conflict of interest policies.
Publisher Copyright:
© European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.
PY - 2022
Y1 - 2022
N2 - We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using the retrieved sentences; and (c) effective and faithful explanations when answers are provided.
AB - We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using the retrieved sentences; and (c) effective and faithful explanations when answers are provided.
UR - http://www.scopus.com/inward/record.url?scp=85144449288&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85144449288&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85144449288
T3 - 2022 Language Resources and Evaluation Conference, LREC 2022
SP - 4552
EP - 4560
BT - 2022 Language Resources and Evaluation Conference, LREC 2022
A2 - Calzolari, Nicoletta
A2 - Bechet, Frederic
A2 - Blache, Philippe
A2 - Choukri, Khalid
A2 - Cieri, Christopher
A2 - Declerck, Thierry
A2 - Goggi, Sara
A2 - Isahara, Hitoshi
A2 - Maegaard, Bente
A2 - Mariani, Joseph
A2 - Mazo, Helene
A2 - Odijk, Jan
A2 - Piperidis, Stelios
PB - European Language Resources Association (ELRA)
Y2 - 20 June 2022 through 25 June 2022
ER -