MICRON: Multigranular Interaction for Contextualizing RepresentatiON in Non-factoid Question Answering

Han, Hojae; Choi, Seungtaek; Park, Haeju; Hwang, Seung Won

doi:10.18653/v1/d19-1601

“…Current models seemingly match similar keywords or phrases of the questions and answers, often without truly understanding them in context. (Rücklé et al, 2019b), ‡ is the MICRON model (Han et al, 2019), is the BERT model in (Ma et al, 2019), and is MV-DASE (Poerner and Schütze, 2019). Table 5: A mistake of MultiCQA RBa-lg (zero-shot transfer) on AskUbuntu.…”

Section: Discussionmentioning

confidence: 99%

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

Rücklé

¹

,

Pfeiffer

²

,

Gurevych

³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines. We also demonstrate that considering a broad selection of source domains is crucial for obtaining the best zero-shot transfer performances, which contrasts the standard procedure that merely relies on the largest and most similar domains. In addition, we extensively study how to best combine multiple source domains. We propose to incorporate self-supervised with supervised multi-task learning on all available source domains. Our best zero-shot transfer model considerably outperforms in-domain BERT and the previous state of the art on six benchmarks. Fine-tuning of our model with in-domain data results in additional large gains and achieves the new state of the art on all nine benchmarks.

show abstract

“…The IR baselines are the same as in §4.1 (TF*IDF for LAS, BM25 for WikiPassageQA and InsuranceQA, and a search engine ranking for SemEval17-the official challenge baseline). (Rücklé et al, 2019b), ‡ is the MICRON model (Han et al, 2019), is the BERT model in (Ma et al, 2019), and is MV-DASE (Poerner and Schütze, 2019).…”

Section: Modelsmentioning

confidence: 99%

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

Rücklé¹,

Pfeiffer²,

Gurevych³

2020

Preprint

View full text Add to dashboard Cite

We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines. We also demonstrate that considering a broad selection of source domains is crucial for obtaining the best zero-shot transfer performances, which contrasts the standard procedure that merely relies on the largest and most similar domains. In addition, we extensively study how to best combine multiple source domains. We propose to incorporate self-supervised with supervised multi-task learning on all available source domains. Our best zero-shot transfer model considerably outperforms in-domain BERT and the previous state of the art on six benchmarks. Fine-tuning of our model with in-domain data results in additional large gains and achieves the new state of the art on all nine benchmarks.

show abstract

“…However, such approach also targets on short answers, not with varying length. Beyond factoid questions, retrieving a paragraph of answering why-or how-questions has been studied (Ruckle, Moosavi, and Gurevych 2019;Han et al 2019;Tan et al 2015). While these approaches can deal with longer answers, they assume that pre-segmented paragraphs are available, which is not available in our problem setting.…”

Section: Text-based Extractive Qamentioning

confidence: 99%

Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos

Lee

¹

,

Duan

²

,

Ji

³

et al. 2020

AAAI

Self Cite

1

0

View full text Add to dashboard Cite

We study the problem of non-factoid QA on instructional videos. Existing work focuses either on visual or textual modality of video content, to find matching answers to the question. However, neither is flexible enough for our problem setting of non-factoid answers with varying lengths. Motivated by this, we propose a two-stage model: (a) multimodal segmentation of video into span candidates and (b) length-adaptive ranking of the candidates to the question. First, for segmentation, we propose Segmenter for generating span candidates of diverse length, considering both textual and visual modality. Second, for ranking, we propose Ranker to score the candidates, dynamically combining the two models with complementary strength for both short and long spans respectively. Experimental result demonstrates that our model achieves state-of-the-art performance.

show abstract

MICRON: Multigranular Interaction for Contextualizing RepresentatiON in Non-factoid Question Answering

Cited by 5 publications

References 15 publications

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos

Contact Info

Product

Resources

About