Spain

Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the \I{de facto} metrics to evaluate tasks such as image captioning and machine translation, despite their known limitations. This is partly due to ease of use, and partly because researchers expect to see them and know how to interpret them. In this paper, we urge the community for more careful consideration of how they automatically evaluate their models by demonstrating important failure cases on multiple datasets, language pairs and tasks. Our experiments show that metrics (i) usually prefer system outputs to human-authored texts, (ii) can be insensitive to correct translations of rare words, (iii) can yield surprisingly high scores when given a single sentence as system output for the entire test set.

COLING 2020

Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

Semantic annotation tasks contain ambiguity and vagueness and require varying degrees of world knowledge. Disagreement is an important indication of these phenomena. Most traditional evaluation methods, however, critically hinge upon the notion of inter-annotator agreement. While alternative frameworks have been proposed, they do not move beyond agreement as the most important indicator of quality. Critically, evaluations usually do not distinguish between instances in which agreement is expected and instances in which disagreement is not only valid but de-sired because it captures the linguistic and cognitive phenomena in the data. We attempt to overcome these limitations using the example of a dataset that provides semantic representations for diagnostic experiments on language models. Ambiguity, vagueness, and difficulty are not only highly relevant for this use-case, but also play an important role in other types of semantic annotation tasks. We establish an additional, agreement-independent quality metric based on answer-coherence and evaluate it in comparison to existing metrics. We compare against a gold standard and evaluate on expected disagreement. Despite generally low agreement, annotations follow expected behavior and have high accuracy when selected based on coherence. We show that combining different quality metrics enables a more comprehensive evaluation than relying exclusively on agreement.


Would you describe a leopard as yellow?
Evaluating crowd annotations with justified and informative disagreement

Emotion recognition in textual conversations (ERTC) plays an important role in a wide range of applications, such as opinion mining, recommender systems, and so on. ERTC, however, is a challenging task. For one thing, speakers often rely on the context and commonsense knowledge to express emotions; for another, most utterances contain neutral emotion in conversations, as a result, the confusion between a few non-neutral utterances and much more neutral ones restrains the emotion recognition performance. In this paper, we propose a novel Knowledge Aware Incremental Transformer with Multi-task Learning (KAITML) to address these challenges. Firstly, we devise a dual-level graph attention mechanism to leverage commonsense knowledge, which augments the semantic information of the utterance. Then we apply the Incremental Transformer to encode multi-turn contextual utterances. Moreover, we are the first to introduce multi-task learning to alleviate the aforementioned confusion and thus further improve the emotion recognition performance. Extensive experimental results show that our KAITML model outperforms the state-of-the-art models across five benchmark datasets.

Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer

Aspect-based sentiment analysis includes opinion aspect extraction and aspect sentiment classification. Researchers have attempted to discover the relationship between these two sub-tasks and have proposed the joint model for solving aspect-based sentiment analysis. However, they ignore a phenomenon: aspect boundary label and sentiment label of the same word can correct each other. To exploit this phenomenon, we propose a novel deep learning model named the label correction model. Specifically, given an input sentence, our model first predicts the aspect boundary label sequence and sentiment label sequence, then re-predicts the aspect boundary (sentiment) label sequence using the embeddings of the previously predicted sentiment (aspect boundary) label. The goal of the re-prediction operation (can be repeated multiple times) is to use the information of the sentiment (aspect boundary) label to correct the wrong aspect boundary (sentiment) label. Moreover, we explore two ways of using label embeddings: add and gate mechanism. We evaluate our model on three benchmark datasets. Experimental results verify that our model achieves state-of-the-art performance compared with several baselines.

Label Correction Model for Aspect-based Sentiment Analysis

Automatic content scoring systems are widely used on short answer tasks to save human effort. However, the use of these systems can invite cheating strategies, such as students writing irrelevant answers in the hopes of gaining at least partial credit. We generate adversarial answers for benchmark content scoring datasets based on different methods of increasing sophistication and show that even simple methods lead to a surprising decrease in content scoring performance. As an extreme example, up to 60% of adversarial answers generated from random shuffling of words in real answers are accepted by a state-of-the-art scoring system. In addition to analyzing the vulnerabilities of content scoring systems, we examine countermeasures such as adversarial training and show that these measures improve system robustness against adversarial answers considerably but do not suffice to completely solve the problem.

The surprising vulnerability of automatic content scoring systems to adversarial input

For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.

Generalized Shortest-Paths Encoders for AMR-to-Text Generation

Most of the aspect-based sentiment analysis research aims at identifying the sentiment polarities toward some explicit aspect terms while ignores implicit aspects in text. To capture both explicit and implicit aspects, we focus on aspect-category based sentiment analysis, which involves joint aspect category detection and category-oriented sentiment classification. However, currently only a few simple studies have focused on this problem. The shortcomings in the way they defined the task make their approaches difficult to effectively learn the inner-relations between categories and the inter-relations between categories and sentiments. In this work, we re-formalize the task as a category-sentiment hierarchy prediction problem, which contains a hierarchy output structure to first identify multiple aspect categories in a piece of text, and then predict the sentiment for each of the identified categories. Specifically, we propose a Hierarchical Graph Convolutional Network (Hier-GCN), where a lower-level GCN is to model the inner-relations among multiple categories, and the higher-level GCN is to capture the inter-relations between aspect categories and sentiments. Extensive evaluations demonstrate that our hierarchy output structure is superior over existing ones, and the Hier-GCN model can consistently achieve the best results on four benchmarks.

Aspect-Category based Sentiment Analysis with Hierarchical Graph
Convolutional Network

Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system. Dif- ferent from most existing methods that rely heavily on manually labeled OOD samples, we focus on the unsupervised OOD detection scenario where there are no labeled OOD samples except for labeled in-domain data. In this paper, we propose a simple but strong generative distance- based classifier to detect OOD samples. We estimate the class-conditional distribution on feature spaces of DNNs via Gaussian discriminant analysis (GDA) to avoid over-confidence problems. And we use two distance functions, Euclidean and Mahalanobis distances, to measure the confi- dence score of whether a test sample belongs to OOD. Experiments on four benchmark datasets show that our method can consistently outperform the baselines.

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

Events in a narrative differ in salience: some are more important to the story than others. Esti- mating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes' definition of event salience and propose several unsupervised methods that require only a pre-trained language model. Evaluating the proposed methods on folktales with event salience annotation, we show that the proposed methods outperform baseline methods and find fine-tuning a language model on narrative texts is a key factor in improving the proposed methods.

Modeling Event Salience in Narratives via Barthes' Cardinal Functions

We propose Pointer- LSTM, a novel LSTM framework which relies on a pointer network to select important words for target prediction. The model maintains a coherent input process for the LSTM modules and makes it possible to change the skip rate during inference. Our evaluation on four public data sets demonstrates that Pointer-LSTM (a) is 1.1x∼3.5x faster than the standard LSTM architecture; (b) is more accurate than Leap-LSTM (the state-of-the-art LSTM skipping model) at high skip rates; and (c) reaches robust accuracy levels even when the skip rate is changed during inference.

Pointing to Select: A Fast Pointer-LSTM for Long Text Classification

Zero-shot slot filling has widely arisen to cope with data scarcity in target domains. However, previous approaches often ignore constraints between slot value representation and related slot description representation in the latent space and lack enough model robustness. In this paper, we propose a Contrastive Zero-Shot Learning with Adversarial Attack (CZSL-Adv) method for the cross-domain slot filling. The contrastive loss aims to map slot value contextual representations to the corresponding slot description representations. And we introduce an adversarial attack training strategy to improve model robustness. Experimental results show that our model significantly outperforms state-of-the-art baselines under both zero-shot and few-shot settings.

Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale

Downloads

Next from COLING 2020

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

Similar lecture

Assessing Humour in Edited News Headlines Using Hand-crafted Features and Online Knowledge Bases

Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale

.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 COLING 2020

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

Similar lecture

Assessing Humour in Edited News Headlines Using Hand-crafted Features and Online Knowledge Bases

Downloads