Thailand

Today&#39;s text classifiers inevitably suffer from unintended dataset biases, especially the document-level label bias and word-level keyword bias, which may hurt models&#39; generalization. Many previous studies employed data-level manipulations or model-level balancing mechanisms to recover unbiased distributions and thus prevent models from capturing the two types of biases. Unfortunately, they either suffer from the extra cost of data collection/selection/annotation or need an elaborate design of balancing strategies. Different from traditional factual inference in which debiasing occurs before or during training, counterfactual inference mitigates the influence brought by unintended confounders after training, which can make unbiased decisions with biased observations. Inspired by this, we propose a model-agnostic text classification debiasing framework -- Corsair, which can effectively avoid employing data manipulations or designing balancing mechanisms. Concretely, Corsair first trains a base model on a training set directly, allowing the dataset biases &#39;poison&#39; the trained model. In inference, given a factual input document, Corsair imagines its two counterfactual counterparts to distill and mitigate the two biases captured by the poisonous model. Extensive experiments demonstrate Corsair&#39;s effectiveness, generalizability and fairness.

ACL-IJCNLP 2021

Counterfactual Inference for Text Classification Debiasing

causal intervention

text classification

counterfactual inference

**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).

Today's text classifiers inevitably suffer from unintended dataset biases, especially the document-level label bias and word-level keyword bias, which may hurt models' generalization. Many previous studies employed data-level manipulations or model-level balancing mechanisms to recover unbiased distributions and thus prevent models from capturing the two types of biases. Unfortunately, they either suffer from the extra cost of data collection/selection/annotation or need an elaborate design of balancing strategies. Different from traditional factual inference in which debiasing occurs before or during training, counterfactual inference mitigates the influence brought by unintended confounders after training, which can make unbiased decisions with biased observations. Inspired by this, we propose a model-agnostic text classification debiasing framework -- Corsair, which can effectively avoid employing data manipulations or designing balancing mechanisms. Concretely, Corsair first trains a base model on a training set directly, allowing the dataset biases 'poison' the trained model. In inference, given a factual input document, Corsair imagines its two counterfactual counterparts to distill and mitigate the two biases captured by the poisonous model. Extensive experiments demonstrate Corsair's effectiveness, generalizability and fairness.

poster

This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decompose an original matrix into central tensors (containing the core information) and auxiliary tensors (with only a small proportion of parameters). With the decomposed MPO structure, we propose a novel fine-tuning strategy by only updating the parameters from the auxiliary tensors, and design an optimization algorithm for MPO-based approximation over stacked network architectures. Our approach can be applied to the original or the compressed PLMs in a general way, which derives a lighter network and significantly reduces the parameters to be fine-tuned. Extensive experiments have demonstrated the effectiveness of the proposed approach in model compression, especially the reduction in fine-tuning parameters (91% reduction on average). The code to reproduce the results of this paper can be found at https://github.com/RUCAIBox/MPOP.

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness. In this work, for the first time, we can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit.
On top of this, we implement a hessian-free method with a model faithfulness guarantee. 
Finally, to compare our method with the others, we propose a semantic-based evaluation metric that can better align with humans' judgment of explanations than the widely adopted diagnostic or re-training measures.
The empirical results on multiple real data sets demonstrate the proposed method's superior performance to popular explanation techniques such as Influence Function or TracIn on semantic evaluation.

On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation

CausaLM: Causal Model Explanation Through Counterfactual Language Models

A growing body of work makes use of probing in order to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the inability to infer behavioral conclusions from probing results, and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded. Our method, Amnesic Probing, follows the intuition that the utility of a property for a given task can be assessed by measuring the influence of a causal intervention that removes it from the representation. Equipped with this new analysis tool, we can ask questions that were not possible before, for example, is part-of-speech information important for word prediction? We perform a series of analyses on BERT to answer these types of questions. Our findings demonstrate that conventional probing performance is not correlated to task importance, and we call for increased scrutiny of claims that draw behavioral or causal conclusions from probing results.

Amnesic Probing: Behavioral Explanation With Amnesic Counterfactuals

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens.

Syntax-Enhanced Pre-trained Model

Unsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain. Existing methods typically require to learn to adapt the target model by exploiting the source data and sharing the network architecture across domains. However, this pipeline makes the source data risky and is inflexible for deploying the target model. This paper tackles a novel setting where only a trained source model is available and different network architectures can be adapted for target domain in terms of deployment environments. We propose a generic framework named \emph{Cross-domain Knowledge Distillation} (CdKD) without needing any source data. CdKD matches the joint distributions between a trained source model and a set of target data during distilling the knowledge from the source model to the target domain. As a type of important knowledge in the source domain, for the first time, the gradient information is exploited to boost the transfer performance. Experiments on cross-domain text classification demonstrate that CdKD achieves superior performance, which verifies the effectiveness in this novel setting.

Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation

The Reading Machine, is a parsing framework that takes as input raw text and performs six standard nlp tasks: tokenization, pos tagging, morphological analysis, lemmatization, dependency parsing and sentence segmentation. It is built upon Transition Based Parsing, and allows implementing a large number of parsing configurations, among which a fully incremental one. Three case studies are presented to highlight the versatility of the framework. The first one explores whether an incremental parser is able to take into account top-down dependencies (i.e. the influence of high level decisions on low level ones), the second compares the performances of an incremental and a pipe-line architecture and the third quantifies the impact of the right context on the predictions made by an incremental parser.

The Reading Machine: a Versatile Framework for Studying Incremental Parsing Strategies

Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing.
Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already.
This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels).
Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.

Levi Graph AMR Parser using Heterogeneous Attention

Domain adaption in syntactic parsing is still a significant challenge. We address the issue of data imbalance between the in-domain and out-of-domain treebank typically used for the problem. We define domain adaptation as a Multi-task learning (MTL) problem, which allows us to train two parsers, one for each domain. Our results show that the MTL approach is beneficial for the smaller treebank. For the larger treebank, we need to use loss weighting in order to avoid a decrease in performance below the single task. In order to determine to what degree the data imbalance between two domains and the domain differences affect results, we also carry out an experiment with two imbalanced in-domain treebanks and show that loss weighting also improves performance in an in-domain setting. Given loss weighting in MTL, we can improve results for both parsers.

Bi-directional Domain Adaptation Using Weighted MTL

Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web review ``Great service!'', the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit arguments dynamically, and experiment with two different transition systems on the improved dataset. We find that certain types of implicit arguments are more difficult to parse than others and that the simpler system is more accurate in recovering implicit arguments, despite having a lower overall parsing score, attesting current reasoning limitations of NLP models. This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.

Downloads

Next from ACL-IJCNLP 2021

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

Similar lecture

Distinct Label Representations for Few-Shot Text Classification