Question Answering (State of the art)

From ACL Wiki
Jump to navigation Jump to search

Answer Sentence Selection

The task of answer sentence selection is designed for the open-domain question answering setting. Given a question and a set of candidate sentences, the task is to choose the correct sentence that contains the exact answer and can sufficiently support the answer choice.

  • QA Answer Sentence Selection Dataset: labeled sentences using TREC QA track data, provided by Mengqiu Wang and first used in Wang et al. (2007).
  • Over time, the original dataset diverged to two versions due to different pre-processing in recent publications: both have the same training set but their development and test sets differ. The Raw version has 82 questions in the development set and 100 questions in the test set; The Clean version (Wang and Ittycheriah et al. 2015, Tan et al. 2015, dos Santos et al. 2016, Wang et al. 2016) removed questions with no answers or with only positive/negative answers, thus has only 65 questions in the development set and 68 questions in the test set.
  • Note: MAP/MRR scores on the two versions of TREC QA data (Clean vs Raw) are not comparable according to Rao et al. (2016).


Algorithm - Raw Version of TREC QA Reference MAP MRR
Punyakanok (2004) Wang et al. (2007) 0.419 0.494
Cui (2005) Wang et al. (2007) 0.427 0.526
Wang (2007) Wang et al. (2007) 0.603 0.685
H&S (2010) Heilman and Smith (2010) 0.609 0.692
W&M (2010) Wang and Manning (2010) 0.595 0.695
Yao (2013) Yao et al. (2013) 0.631 0.748
S&M (2013) Severyn and Moschitti (2013) 0.678 0.736
Shnarch (2013) - Backward Shnarch (2013) 0.686 0.754
Yih (2013) - LCLR Yih et al. (2013) 0.709 0.770
Yu (2014) - TRAIN-ALL bigram+count Yu et al. (2014) 0.711 0.785
W&N (2015) - Three-Layer BLSTM+BM25 Wang and Nyberg (2015) 0.713 0.791
Feng (2015) - Architecture-II Tan et al. (2015) 0.711 0.800
S&M (2015) Severyn and Moschitti (2015) 0.746 0.808
Yang (2016) - Attention-Based Neural Matching Model Yang et al. (2016) 0.750 0.811
Tay (2017) - Holographic Dual LSTM Architecture Tay et al. (2017) 0.750 0.815
H&L (2016) - Pairwise Word Interaction Modelling He and Lin (2016) 0.758 0.822
H&L (2015) - Multi-Perspective CNN He and Lin (2015) 0.762 0.830
Tay (2017) - HyperQA (Hyperbolic Embeddings) Tay et al. (2017) 0.770 0.825
Rao (2016) - PairwiseRank + Multi-Perspective CNN Rao et al. (2016) 0.780 0.834
Rao (2019) - Hybrid Co-Attention Network (HCAN) Rao et al. (2019) 0.774 0.843
Tayyar Madabushi (2018) - Question Classification + PairwiseRank + Multi-Perspective CNN Tayyar Madabushi et al. (2018) 0.836 0.863
Kamath (2019) - Question Classification + RNN + Pre-Attention Kamath et al. (2019) 0.852 0.891
Laskar et al. (2020) - CETE (RoBERTa-Large) Laskar et al. (2020) 0.950 0.980


Algorithm - Clean Version of TREC QA Reference MAP MRR
W&I (2015) Wang and Ittycheriah (2015) 0.746 0.820
Tan (2015) - QA-LSTM/CNN+attention Tan et al. (2015) 0.728 0.832
dos Santos (2016) - Attentive Pooling CNN dos Santos et al. (2016) 0.753 0.851
Wang et al. (2016) - L.D.C Model Wang et al. (2016) 0.771 0.845
H&L (2015) - Multi-Perspective CNN He and Lin (2015) 0.777 0.836
Tay et al. (2017) - HyperQA (Hyperbolic Embeddings) Tay et al. (2017) 0.784 0.865
Rao et al. (2016) - PairwiseRank + Multi-Perspective CNN Rao et al. (2016) 0.801 0.877
Wang et al. (2017) - BiMPM Wang et al. (2017) 0.802 0.875
Bian et al. (2017) - Compare-Aggregate Bian et al. (2017) 0.821 0.899
Shen et al. (2017) - IWAN Shen et al. (2017) 0.822 0.889
Tran et al. (2018) - IWAN + sCARNN Tran et al. (2018) 0.829 0.875
Tay et al. (2018) - Multi-Cast Attention Networks (MCAN) Tay et al. (2018) 0.838 0.904
Tayyar Madabushi (2018) - Question Classification + PairwiseRank + Multi-Perspective CNN Tayyar Madabushi et al. (2018) 0.865 0.904
Yoon et al. (2019) - Compare-Aggregate + LanguageModel + LatentClustering Yoon et al. (2019) 0.868 0.928
Lai et al. (2019) - BERT + GSAMN + Transfer Learning Lai et al. (2019) 0.914 0.957
Garg et al. (2019) - TANDA-RoBERTa (ASNQ, TREC-QA) Garg et al. (2019) 0.943 0.974
Laskar et al. (2020) - CETE (RoBERTa-Large) Laskar et al. (2020) 0.936 0.978

References