Leverage Unlabeled Data for Abstractive Speech Summarization with
Self-Supervised Learning and Back-Summarization
- URL: http://arxiv.org/abs/2007.15296v2
- Date: Thu, 17 Sep 2020 10:12:03 GMT
- Title: Leverage Unlabeled Data for Abstractive Speech Summarization with
Self-Supervised Learning and Back-Summarization
- Authors: Paul Tardy, Louis de Seynes, Fran\c{c}ois Hernandez, Vincent Nguyen,
David Janiszek, Yannick Est\`eve
- Abstract summary: Supervised approaches for Neural Abstractive Summarization require large annotated corpora that are costly to build.
We present a French meeting summarization task where reports are predicted based on the automatic transcription of the meeting audio recordings.
We report large improvements compared to the previous baseline for both approaches on two evaluation sets.
- Score: 6.465251961564605
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Supervised approaches for Neural Abstractive Summarization require large
annotated corpora that are costly to build. We present a French meeting
summarization task where reports are predicted based on the automatic
transcription of the meeting audio recordings. In order to build a corpus for
this task, it is necessary to obtain the (automatic or manual) transcription of
each meeting, and then to segment and align it with the corresponding manual
report to produce training examples suitable for training. On the other hand,
we have access to a very large amount of unaligned data, in particular reports
without corresponding transcription. Reports are professionally written and
well formatted making pre-processing straightforward. In this context, we study
how to take advantage of this massive amount of unaligned data using two
approaches (i) self-supervised pre-training using a target-side denoising
encoder-decoder model; (ii) back-summarization i.e. reversing the summarization
process by learning to predict the transcription given the report, in order to
align single reports with generated transcription, and use this synthetic
dataset for further training. We report large improvements compared to the
previous baseline (trained on aligned data only) for both approaches on two
evaluation sets. Moreover, combining the two gives even better results,
outperforming the baseline by a large margin of +6 ROUGE-1 and ROUGE-L and +5
ROUGE-2 on two evaluation sets
Related papers
- BERM: Training the Balanced and Extractable Representation for Matching
to Improve Generalization Ability of Dense Retrieval [54.66399120084227]
We propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM.
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
arXiv Detail & Related papers (2023-05-18T15:43:09Z) - Efficient Few-Shot Fine-Tuning for Opinion Summarization [83.76460801568092]
Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples.
We show that a few-shot method based on adapters can easily store in-domain knowledge.
We show that this self-supervised adapter pre-training improves summary quality over standard fine-tuning by 2.0 and 1.3 ROUGE-L points on the Amazon and Yelp datasets.
arXiv Detail & Related papers (2022-05-04T16:38:37Z) - Learning Bidirectional Translation between Descriptions and Actions with
Small Paired Data [5.188295416244741]
This study proposes a two-stage training method for bidirectional translation.
We train recurrent autoencoders (RAEs) for descriptions and actions with a large amount of non-paired data.
Then, we fine-tune the entire model to bind their intermediate representations using small paired data.
arXiv Detail & Related papers (2022-03-08T17:39:16Z) - Attention-based Multi-hypothesis Fusion for Speech Summarization [83.04957603852571]
Speech summarization can be achieved by combining automatic speech recognition (ASR) and text summarization (TS)
ASR errors directly affect the quality of the output summary in the cascade approach.
We propose a cascade speech summarization model that is robust to ASR errors and that exploits multiple hypotheses generated by ASR to attenuate the effect of ASR errors on the summary.
arXiv Detail & Related papers (2021-11-16T03:00:29Z) - Improving Punctuation Restoration for Speech Transcripts via External
Data [1.4335946386597276]
We tackle the punctuation restoration problem specifically for the noisy text.
We introduce a data sampling technique based on an n-gram language model to sample more training data.
The proposed approach outperforms the baseline with an improvement of 1:12% F1 score.
arXiv Detail & Related papers (2021-10-01T17:40:55Z) - MeetSum: Transforming Meeting Transcript Summarization using
Transformers! [2.1915057426589746]
We utilize a Transformer-based Pointer Generator Network to generate abstract summaries for meeting transcripts.
This model uses 2 LSTMs as an encoder and a decoder, a Pointer network which copies words from the inputted text, and a Generator network to produce out-of-vocabulary words.
We show that training the model on a news summary dataset and using zero-shot learning to test it on the meeting dataset proves to produce better results than training it on the AMI meeting dataset.
arXiv Detail & Related papers (2021-08-13T16:34:09Z) - Summary-Source Proposition-level Alignment: Task, Datasets and
Supervised Baseline [94.0601799665342]
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task.
We propose establishing summary-source alignment as an explicit task, while introducing two major novelties.
We create a novel training dataset for proposition-level alignment, derived automatically from available summarization evaluation data.
We present a supervised proposition alignment baseline model, showing improved alignment-quality over the unsupervised approach.
arXiv Detail & Related papers (2020-09-01T17:27:12Z) - Entity and Evidence Guided Relation Extraction for DocRED [33.69481141963074]
We pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task.
We introduce entity-guided sequences as inputs to a pre-trained language model (e.g. BERT, RoBERTa)
These entity-guided sequences help a pre-trained language model (LM) to focus on areas of the document related to the entity.
We evaluate our E2GRE approach on DocRED, a recently released large-scale dataset for relation extraction.
arXiv Detail & Related papers (2020-08-27T17:41:23Z) - Align then Summarize: Automatic Alignment Methods for Summarization
Corpus Creation [8.029049649310211]
State-of-the-art on automatic text summarization mostly revolves around news articles.
Our work consists in segmenting and aligning transcriptions with respect to reports, to get a suitable dataset for neural summarization.
We report automatic alignment and summarization performances on a novel corpus of aligned public meetings.
arXiv Detail & Related papers (2020-07-15T17:03:34Z) - Extractive Summarization as Text Matching [123.09816729675838]
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
We formulate the extractive summarization task as a semantic text matching problem.
We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
arXiv Detail & Related papers (2020-04-19T08:27:57Z) - Pre-training for Abstractive Document Summarization by Reinstating
Source Text [105.77348528847337]
This paper presents three pre-training objectives which allow us to pre-train a Seq2Seq based abstractive summarization model on unlabeled text.
Experiments on two benchmark summarization datasets show that all three objectives can improve performance upon baselines.
arXiv Detail & Related papers (2020-04-04T05:06:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.