Thailand

Do state-of-the-art natural language understanding models care about word order? Not always! We found 75% to 90% of the correct predictions of BERT-based classifiers, trained on many GLUE tasks, remain constant after input words are randomly shuffled. Although BERT embeddings are famously contextual, the contribution of each individual word to downstream tasks is almost unchanged even after the word&#39;s context is shuffled. BERT-based models are able to exploit superficial cues (e.g. the sentiment of keywords in sentiment analysis; or the word-wise similarity between sequence-pair inputs in natural language inference) to make correct decisions when tokens are arranged in random orders. Encouraging classifiers to capture word order information improves the performance on most GLUE tasks and SQuAD 2.0. Our work suggests that many GLUE tasks are not challenging machines to understand the meaning of a sentence.

ACL-IJCNLP 2021

Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

word-order-sensitivity.

word-order

explainable-ai

glue

bert

**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).

Do state-of-the-art natural language understanding models care about word order? Not always! We found 75% to 90% of the correct predictions of BERT-based classifiers, trained on many GLUE tasks, remain constant after input words are randomly shuffled. Although BERT embeddings are famously contextual, the contribution of each individual word to downstream tasks is almost unchanged even after the word's context is shuffled. BERT-based models are able to exploit superficial cues (e.g. the sentiment of keywords in sentiment analysis; or the word-wise similarity between sequence-pair inputs in natural language inference) to make correct decisions when tokens are arranged in random orders. Encouraging classifiers to capture word order information improves the performance on most GLUE tasks and SQuAD 2.0. Our work suggests that many GLUE tasks are not challenging machines to understand the meaning of a sentence.

technical paper

In this paper, we introduce Integrated Directional Gradients (IDG), a method for attributing importance scores to groups of features, indicating their relevance to the output of a neural network model for a given input. The success of Deep Neural Networks has been attributed to their ability to capture higher level feature interactions. Hence, in the last few years capturing the importance of these feature interactions has received increased prominence in ML interpretability literature. In this paper, we formally define the feature group attribution problem and outline a set of axioms that any intuitive feature group attribution method should satisfy. Earlier, cooperative game theory inspired axiomatic methods only borrowed axioms from solution concepts (such as Shapley value) for individual feature attributions and introduced their own extensions to model interactions. In contrast, our formulation is inspired by axioms satisfied by characteristic functions as well as solution concepts in cooperative game theory literature. We believe that characteristic functions are much better suited to model importance of groups compared to just solution concepts. We demonstrate that our proposed method, IDG, satisfies all the axioms. Using IDG we analyze two state-of-the-art text classifiers on three benchmark datasets for sentiment analysis. Our experiments show that IDG is able to effectively capture semantic interactions in linguistic models via negations and conjunctions.

Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs themselves, suggesting this assumption may not have merit. We build on the recent work exploring the interpretability of attention; we design a set of experiments to help us understand how sparsity affects our ability to use attention as an explainability tool. On three text classification tasks, we verify that only a weak relationship between inputs and co-indexed intermediate representations exists—under sparse attention and otherwise. Further, we do not find any plausible mappings from sparse attention distributions to a sparse set of influential inputs through other avenues. Rather, we observe in this setting that inducing sparsity may make it less plausible that attention can be used as a tool for understanding model behavior.

Is Sparse Attention more Interpretable?

Mechanisms for encoding positional information are central for transformer-based language models. In this paper, we analyze the position embeddings of existing language models, finding strong evidence of translation invariance, both for the embeddings themselves and for their effect on self-attention. The degree of translation invariance increases during training and correlates positively with model performance. Our findings lead us to propose translation-invariant self-attention (TISA), which accounts for the relative position between tokens in an interpretable fashion without needing conventional position embeddings. Our proposal has several theoretical advantages over existing position-representation approaches. Proof-of-concept experiments show that it improves on regular ALBERT on GLUE tasks, while only adding orders of magnitude less positional parameters.

The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models

In conversation, uptake happens when a speaker builds on the contribution of their interlocutor by, for example, acknowledging, repeating or reformulating what they have said. In education, teachers’ uptake of student contributions has been linked to higher student achievement. Yet measuring and improving teachers' uptake at scale is challenging, as existing methods require expensive annotation by experts. We propose a framework for computationally measuring uptake, by (1) releasing a dataset of student-teacher exchanges extracted from US math classroom transcripts annotated for uptake by experts; (2) formalizing uptake as pointwise Jensen-Shannon Divergence (pJSD), estimated via next utterance classification; (3) conducting a linguistically-motivated comparison of different unsupervised measures and (4) correlating these measures with educational outcomes. We find that although repetition captures a significant part of uptake, pJSD outperforms repetition-based baselines, as it is capable of identifying a wider range of uptake phenomena like question answering and reformulation. We apply our uptake measure to three different educational datasets with outcome indicators. Unlike baseline measures, pJSD correlates significantly with instruction quality in all three, providing evidence for its generalizability and for its potential to serve as an automated professional development tool for teachers.

Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions

We present a human-and-model-in-the-loop process for dynamically generating datasets and training better performing and more robust hate detection models. We provide a new dataset of 40,000 entries, generated and labelled by trained annotators over four rounds of dynamic data creation. It includes 15,000 challenging perturbations and each hateful entry has fine-grained labels for the type and target of hate. Hateful entries make up 54% of the dataset, which is substantially higher than comparable datasets. We show that model performance is substantially improved using this approach. Models trained on later rounds of data collection perform better on test sets and are harder for annotators to trick. They also have better performance on HateCheck, a suite of functional tests for online hate detection. We provide the code, dataset and annotation guidelines for other researchers to use.

Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection

To defend against machine-generated fake news, an effective mechanism is urgently needed. We contribute a novel benchmark for fake news detection at the knowledge element level, as well as a solution for this task which incorporates cross-media consistency checking to detect the fine-grained knowledge elements making news articles misinformative. Due to training data scarcity, we also formulate a novel data synthesis method by manipulating knowledge elements within the knowledge graph to generate noisy training data with specific, hard to detect, known inconsistencies. Our detection approach outperforms the state-of-the-art (up to 16.8% accuracy gain), and more critically, yields fine-grained explanations.

InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection

Prior work has revealed that positive words occur more frequently than negative words in human expressions, which is typically attributed to positivity bias, a tendency for people to report positive views of reality. But what about the language used in negative reviews? Consistent with prior work, we show that English negative reviews tend to contain more positive words than negative words, using a variety of datasets. We reconcile this observation with prior findings on the pragmatics of negation, and show that negations are commonly associated with positive words in negative reviews. Furthermore, in negative reviews, the majority of sentences with positive words express negative opinions based on sentiment classifiers, indicating some form of negation.

On Positivity Bias in Negative Reviews

To quantify how well natural language understanding models can capture consistency in a general conversation, we introduce the DialoguE COntradiction DEtection task (DECODE) and a new conversational dataset containing both human-human and human-bot contradictory dialogues. 
We show that: 
(i) our newly collected dataset is notably more effective at providing supervision for the dialogue contradiction detection task than existing NLI data including those aimed to cover the dialogue domain;
(ii) Transformer models that explicitly hinge on utterance structures for dialogue contradiction detection are more robust and generalize well on both analysis and out-of-distribution dialogues than standard (unstructured) Transformers.
We also show that our best contradiction detection model correlates well with human judgments and further provide evidence for its usage in both automatically evaluating and improving the consistency of state-of-the-art generative chatbots.

I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling

A good open-domain chatbot should avoid presenting contradictory responses about facts or opinions in a conversational session, known as its consistency capacity. However, evaluating the consistency capacity of a chatbot is still challenging. Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias. In this paper, we propose the \textbf{A}ddressing \textbf{I}nquiries about \textbf{H}istory (\textbf{AIH}), an efficient and practical framework for the consistency evaluation. At the conversation stage, \textbf{AIH} attempts to address appropriate inquiries about the dialogue history to induce the chatbot to redeclare the historical facts or opinions. We carry out the conversation between chatbots, which is more efficient than the human-bot interaction and can also alleviate the subjective bias. In this way, we manage to rapidly obtain a dialog session that contains responses with high contradiction possibilities. At the contradiction recognition stage, we can either employ human judges or a natural language inference (NLI) model to recognize whether the answers to the inquiries are contradictory with history. Finally, we are able to rank chatbots according to the contradiction statistics. Experiments on open-domain chatbots show that our approach can efficiently and reliably assess the consistency capacity of chatbots and achieve a high ranking correlation with the human evaluation. We release the framework and hope to help improve the consistency capacity of chatbots.\footnote{\url{https://github.com/ictnlp/AIH}}

Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency

We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradient-based visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change the word order and points out the future research direction that worth being explored more on non-autoregressive speech translation.

Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

Downloads

Next from ACL-IJCNLP 2021

Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models

Similar lecture

End-to-End Self-Debiasing Framework for Robust NLU Training

Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models

Similar lecture

End-to-End Self-Debiasing Framework for Robust NLU Training

Downloads