Thailand

In order to deeply understand the capability of pretrained language models in text generation and conduct a diagnostic evaluation, we propose TGEA, an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models (PLMs). We use carefully selected prompt words to guide GPT-2 to generate candidate sentences, from which we select 47K for error annotation. Crowdsourced workers manually check each of these sentences and detect 12k erroneous sentences. We create an error taxonomy to cover 24 types of errors occurring in these erroneous sentences according to the nature of errors with respect to linguistics and knowledge (e.g., common sense). For each erroneous span in PLM-generated sentences, we also detect another span that is closely associated with it. Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. This is the first dataset with comprehensive annotations for PLM-generated texts, which facilitates the diagnostic evaluation of PLM-based text generation. Furthermore, we use TGEA as a benchmark dataset and propose a series of automatic diagnosis tasks, including error detection, error type classification, associated span detection, error rationale generation, to further promote future study on the automatic error detection and correction on texts generated by pretrained language models.

IJCNLP-AACL 2021

TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models

grammatical error correction datasets generated by pretrained language models

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

poster

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two innovations: 1) it aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism; 2) it uses a shallow decoder instead of the conventional Transformer architecture with balanced encoder-decoder depth to reduce the computational cost during inference. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield identical predictions to greedy decoding but with significant speedup for online inference. Its combination with the shallow decoder could offer an even higher online inference speedup over the powerful Transformer baseline without quality loss. Not only does our approach allow a single model to achieve the state-of-the-art results in English GEC benchmarks: 66.4 F0.5 in the CoNLL-14 and 72.9 F0.5 in the BEA-19 test set with an almost 10x online inference speedup over the Transformer-big model, but also it is easily adapted to other languages. Our code is available at https://github.com/AutoTemp/Shallow-Aggressive-Decoding.

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

The multimodality problem has become a major challenge of existing non-autoregressive generation (NAG) systems. A common solution often resorts to sequence-level knowledge distillation by rebuilding the training dataset through autoregressive generation (hereinafter known as ``teacher AG"). The success of such methods may largely depend on a latent assumption, i.e., the teacher AG is superior to the NAG model. However, in this work, we experimentally reveal that this assumption does not always hold for the text generation tasks like text summarization and story ending generation. To provide a feasible solution to the multimodality problem of NAG, we propose incorporating linguistic structure (Part-of-Speech sequence in particular) into NAG inference instead of relying on teacher AG. More specifically, the proposed POS-constrained Parallel Decoding (POSPD) method aims at providing a specific POS sequence to constrain the NAG model during decoding. Our experiments demonstrate that POSPD consistently improves NAG models on four text generation tasks to a greater extent compared to knowledge distillation. This observation validates the necessity of exploring the alternatives for sequence-level knowledge distillation.

POS-Constrained Parallel Decoding for Non-autoregressive Generation

This paper describes our system participated in Task 7 of SemEval-2021: Detecting and Rating Humor and Offense. The task is designed to detect and score humor and offense which are influenced by subjective factors. In order to obtain semantic information from a large amount of unlabeled data, we applied unsupervised pre-trained language models. By conducting research and experiments, we found that the ERNIE 2.0[1] and DeBERTa[2] pre- trained models achieved impressive performance in various subtasks. Therefore, we applied the above pre-trained models to fine-tune the downstream neural network. In the process of fine-tuning the model, we adopted multi-task training strategy and ensemble learning method. Based on the above strategy and method, we achieved RMSE of 0.4959 for sub-task 1b, and finally won the first place.

abcbpc at SemEval-2021 Task 7: ERNIE-based Multi-Task Model for Detecting and Rating Humor and Offense

This presentation describes a system to predict the complexity of words for the Lexical Complexity Prediction (LCP) shared task hosted at SemEval 2021 (Task 1) with a new annotated English dataset with a Likert scale. Located in the Lexical Semantics track, the task consisted of predicting the complexity value of the words in context. A machine learning approach was carried out based on the frequency of the words and several characteristics added at word level. Over these features, a supervised random forest regression algorithm was trained. Several runs were performed with different values to observe the performance of the algorithm. For
the evaluation, our best results reported a M.A.E of 0.07347, M.S.E. of 0.00938, and R.M.S.E. of 0.096871. Our experiments showed that, with a greater number of characteristics, the precision of the classification increases.

Complex word identification using Word-level features.

Source-free domain adaptation is an emerging line of work in deep learning research since it is closely related to the real world environment. We study the domain adaption in the sequence labeling problem where the model trained on the source domain data is given. We propose two methods: Self-Adapter and Selective Classifier Training. Self-Adapter is a training method that uses sentence-level pseudo- labels filtered by the self-entropy threshold to provide supervision to the whole model. Selective Classifier Training uses token-level pseudo-labels and supervises only the classification layer of the model. The proposed methods are evaluated on data provided by SemEval-2021 task 10 and Self-Adapter achieves 2nd rank performance.

Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation

Humor and Offense are highly subjective due to multiple word senses, cultural knowledge, and pragmatic competence. Hence, accurately detecting humorous and offensive texts has several compelling use cases in Recommendation Systems and Personalized Content Moderation. However, due to the lack of an extensive labeled dataset, most prior works in this domain haven’t explored large neural models for subjective humor understanding. This paper explores whether large neural models and their ensembles can capture the intricacies associated with humor/offense detection and rating. Our experiments on the SemEval-2021 Task 7: HaHackathon show that we can develop reasonable humor and offense detection systems with such models. Our models are ranked third in subtask 1b and consistently ranked around the top 33% of the leaderboard for the remaining subtasks.

Humor@IITK at SemEval-2021 Task 7: Large Language Models for Quantifying Humor and Offensiveness

This paper describes our system ECNU_ICA_1 for SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. For this task, we utilize knowledge-enhanced Graph Attention Networks with a novel semantic space transformation strategy. It leverages heterogeneous knowledge to learn adequate evidences, and seeks for an effective semantic space of abstract concepts to better improve the ability of a machine in understanding abstract meanings of natural language. Experimental results show that our system achieves strong performance on this task in terms of both imperceptibility and nonspecificity.

ECNU_ICA_1 at SemEval-2021 Task 4: Knowledge-Enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning

Given a fill-in-the-blank-type question and a corresponding context, the task is to predict the most suitable word from a list of 5 options. 
Our approaches for subtasks:
- Imperceptibility (subtask-I) - Linguistic Feature Engineering
- Non-Specificity (subtask-II) - Information from hypernyms and hyponyms from WordNet and Augmentation.
- Transformers-based models with MLM task to build our Fill-in-the-blank (FitB) models.
- Two auxiliary approaches: Chunk Voting and Max Context, to take care of input length restrictions for BERT, etc.

Improving Reading Comprehension with Abstract Words using Augmentation, Linguistic Features and Voting

This paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing. We show that self-training, active learning and data augmentation techniques can improve the generalization ability of the model on the unlabeled target domain data without accessing source domain data. We also perform detailed ablation studies and error analyses for our time expression recognition systems to identify the source of the performance improvement and give constructive feedback on the temporal normalization annotation guidelines.

TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models

Downloads

Next from IJCNLP-AACL 2021

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

Similar lecture

Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children’s mindreading ability