Papers › Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based...

Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering

7 Apr 2020ACL 2020 6arXiv:2004.03561archive 2025-07-28

Changmao Li, Jinho D. Choi

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts. Then, multi-task learning between the utterance prediction and the token span prediction is applied to fine-tune for span-based question answering (QA). Our approach is evaluated on the FriendsQA dataset and shows improvements of 3.8% and 1.4% over the two state-of-the-art transformer models, BERT and RoBERTa, respectively.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

emorynlp/friendsqa mentioned in paperpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingMulti-Task LearningPredictionQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering FriendsQA Li and Choi - RoBERTa EM 53.5 #3 of 6 Archive leaderboard report
Question Answering FriendsQA Li and Choi - RoBERTa F1 69.6 #3 of 6 Archive leaderboard report
Question Answering FriendsQA Li and Choi - BERT EM 46.8 #5 of 6 Archive leaderboard report
Question Answering FriendsQA Li and Choi - BERT F1 63.1 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionRoBERTaSoftmaxTransformerWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections