Croatia

Explanation prompts ask language models to not only assign a particular label to a given
input, such as true, entailment, or contradiction in the case of natural language inference but also to generate a free-text explanation that supports this label. For example: &quot;This is {label} because {explanation}.” While this type of prompt was originally introduced with the aim of improving model interpretability, we show
here that explanation prompts also improve robustness to adversarial perturbations in natural
language inference benchmarks. Compared to prompting for labels only, explanation prompting consistently yields stronger performance on adversarial benchmarks, outperforming the state of the art on Adversarial Natural Language Inference, Counterfactually-Augmented Natural Language Inference, and SNLI-Hard datasets. We argue that the increase in robustness is due to the fact that prompting for explanations weakens superficial cues. Specifically, single tokens that are highly predictive of the correct answer in the label-only setting become uninformative when the model also has to generate explanations.

EACL 2023

Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}

explanation

superficial cues

prompting

robustness

Explanation prompts ask language models to not only assign a particular label to a given
input, such as true, entailment, or contradiction in the case of natural language inference but also to generate a free-text explanation that supports this label. For example: "This is {label} because {explanation}.” While this type of prompt was originally introduced with the aim of improving model interpretability, we show
here that explanation prompts also improve robustness to adversarial perturbations in natural
language inference benchmarks. Compared to prompting for labels only, explanation prompting consistently yields stronger performance on adversarial benchmarks, outperforming the state of the art on Adversarial Natural Language Inference, Counterfactually-Augmented Natural Language Inference, and SNLI-Hard datasets. We argue that the increase in robustness is due to the fact that prompting for explanations weakens superficial cues. Specifically, single tokens that are highly predictive of the correct answer in the label-only setting become uninformative when the model also has to generate explanations.

findings / work in progress

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

We introduce \dataset, a novel vision-language benchmark for human activity planning. It is designed for a task where embodied AI agents can reason and forecast future actions of humans based on video clips about their initial activities and intents in text. The dataset consists of 2.9k videos from \charades extended with intents via crowdsourcing, a multi-choice question test set, and four strong baselines. One of the baselines implements a neurosymbolic approach based on a multi-modal knowledge base (MKB), while the other ones are deep generative models adapted from recent state-of-the-art (SOTA) methods. According to our extensive experiments, the key challenges are compositional generalization and effective use of information from both modalities.

ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities

Machine translation (MT) operates on the premise of an interlingua which abstracts away from surface form while preserving meaning. A decade ago the idea of using round-trip MT to guide grammatical error correction was proposed as a way to abstract away from potential errors in surface forms (Madnani _et_ _al_., 2012). At the time, it did not pan out due to the low quality of MT systems of the day. Today much stronger MT systems are available so we re-evaluate this idea across five languages and models of various sizes. We find that for extra large models input augmentation through round-trip MT has little to no effect. For more 'workable' model sizes, however, it yields consistent improvements, sometimes bringing the performance of a _base_ or _large_ model up to that of a _large_ or _xl_ model, respectively. The round-trip translation comes at a computational cost though, so one would have to determine whether to opt for a larger model or for input augmentation on a case-by-case basis.

Grammatical Error Correction through Round-Trip Machine Translation

Pre-training masked language models (MLMs) with artificial data has been proven beneficial for several natural language processing tasks such as natural language understanding and summarization; however, it has been less explored for neural machine translation (NMT).
A previous study revealed the benefit of transfer learning for NMT in a limited setup, which differs from MLM.
In this study, we prepared two kinds of artificial data and compared the translation performance of NMT when pre-trained with MLM.
In addition to the random sequences, we created artificial data mimicking token frequency information from the real world.
Our results showed that pre-training the models with artificial data by MLM improves translation performance in low-resource situations.
Additionally, we found that pre-training on artificial data created considering token frequency information facilitates improved performance.

Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation?

Large Language Models such as GPT-3 are well-suited for text prediction tasks, which can help and delight users during text composition. LLMs are known to generate ethically inappropriate predictions even for seemingly innocuous contexts. Toxicity detection followed by filtering is a common strategy for mitigating the harm from such predictions. However, as we shall argue in this paper, in the context of text prediction, it is not sufficient to detect and filter toxic content. One also needs to ensure factual correctness and group-level fairness of the predictions; failing to do so can make the system ineffective and nonsensical at best, and unfair and detrimental to the users at worst. 
We discuss the gaps and challenges of toxicity detection approaches - from blocklist-based approaches to sophisticated state-of-the-art neural classifiers - by evaluating them on the text prediction task for English against a manually crafted CheckList of harms targeted at different groups and different levels of severity.

Performance and Risk Trade-offs for Multi-word Text Prediction at Scale

Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguistic style and visual content. To overcome this drawback, we propose style-aware contrastive learning for multi-style image captioning. First, we present a style-aware visual encoder with contrastive learning to mine potential visual content relevant to style. Moreover, we propose a style-aware triplet contrast objective to distinguish whether the image, style and caption matched. To provide positive and negative samples for contrastive learning, we present three retrieval schemes: object-based retrieval, RoI-based retrieval and triplet-based retrieval, and design a dynamic trade-off function to calculate retrieval scores. Experimental results demonstrate that our approach achieves state-of-the-art performance. In addition, we conduct an extensive analysis to verify the effectiveness of our method.

Style-Aware Contrastive Learning for Multi-Style Image Captioning

In the task of incremental few-shot relation classification, model performance is always limited by the incompatibility between the base feature embedding space and the novel feature embedding space. To tackle the issue, we propose a novel model named ICA-Proto: Iterative Cross Alignment prototypical network. Specifically, we incorporate the query representation into the encoding of novel prototypes and utilize the query-aware prototypes to update the query representation at the same time. Further, we implement the above process iteratively to achieve more interaction. In addition, a novel prototype quadruplet loss is designed to regulate the spatial distributions of embedding space, so as to make it easier for the relation classification. Experimental results on two benchmark datasets demonstrate that ICA-Proto significantly outperforms the state-of-the-art baseline model.

ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification

We present a large, multilingual study into how vision constrains linguistic choice, covering four languages and five linguistic properties, such as verb transitivity or use of numerals. 
We propose a novel method that leverages existing corpora of images with captions written by native speakers, and apply it to nine corpora, comprising 600k images and 3M captions. 
We study the relation between visual input and linguistic choices by training classifiers to predict the probability of expressing a property from raw images, and find evidence supporting the claim that linguistic properties are constrained by visual context across languages. 
We complement this investigation with a corpus study, taking the test case of numerals. Specifically, we use existing annotations (number or type of objects) to investigate the effect of different visual conditions on the use of numeral expressions in captions, and show that similar patterns emerge across languages.
Our methods and findings both confirm and extend existing research in the cognitive literature. We additionally discuss possible applications for language generation.

A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions

In this paper, we explore how much syntactic supervision is "good enough" to make language models (LMs) more human-like. Specifically, we propose the new method called syntactic ablation, where syntactic LMs, namely Recurrent Neural Network Grammars (RNNGs), are gradually ablated from full syntactic supervision to zero syntactic supervision (≈ unidirectional LSTM) by preserving NP, VP, PP, SBAR nonterminal symbols and the combinations thereof. The 17 ablated grammars are then evaluated via targeted syntactic evaluation on the SyntaxGym benchmark. The results of our syntactic ablation demonstrated that (i) the RNNG with zero syntactic supervision underperformed the RNNGs with some syntactic supervision, (ii) the RNNG with full syntactic supervision underperformed the RNNGs with less syntactic supervision, and (iii) the RNNG with mild syntactic supervision achieved the best performance comparable to the state-of-the-art GPT-2-XL. Those results may suggest that the "good enough" approach to language processing seems to make LMs more human-like.

How Much Syntactic Supervision is "Good Enough"?

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results
in various tasks requiring semantic understanding. However, obtaining embeddings at the document level is challenging due to computational requirements and lack of appropriate data. Instead, most approaches fall back on computing document embeddings based on sentence representations. Although there exist architectures and models to encode documents fully, they are in general limited to English and few other high-resourced languages. In this work, we provide a systematic comparison of methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models. We compare input token number truncation, sentence averaging as well as some simple windowing and in some cases new augmented and learnable approaches, on 3 multi- and cross-lingual tasks in 8 languages belonging to 3 different language families. Our task-based extrinsic evaluations show that, independently of the language, a clever combination of sentence embeddings is usually better than encoding the full document as a single unit, even when this is possible. We demonstrate that while a simple sentence average results in a strong baseline for classification tasks, more complex combinations are necessary for semantic tasks

Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?

In this work we study user controlled table-to-text generation where users explore the content in a table by selecting cells and reading a natural language description thereof automatically produce by a natural language generator. Such generation models usually learn from carefully selected cell combinations (clean cell selections); however, in practice users may select unexpected, redundant, or incoherent cell combinations (noisy cell selections). In experiments, we find that models perform well on test sets coming from the same distribution as the train data but their performance drops when evaluated on realistic noisy user inputs. We propose a fine-tuning regime with additional user-simulated noisy cell selections. Models fine-tuned with the proposed regime gain 4.85 BLEU points on user noisy test cases and 1.4 on clean test cases; and achieve comparable state-of-the-art performance on the ToTTo dataset.

Downloads

Next from EACL 2023

ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities