Malta

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and elucidated with much smaller evaluation sets. We first show that in six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We build upon this phenomenon to propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the entire dataset. Anchor points reliably rank models: across 87 diverse language model-prompt pairs, evaluating models using 1-30 anchor points outperforms uniform sampling and other baselines at accurately ranking models. Moreover, just a dozen anchor points can be used to estimate model per-class predictions on all other points in a dataset with low error, sufficient for gauging where the model is likely to fail. Lastly, we present Anchor Point Maps for visualizing these insights and facilitating comparisons of the performance of different models on various regions within the dataset distribution.

EACL 2024

Anchor Points: Benchmarking Models with Much Fewer Examples

correlations

efficient

data selection

interpretability

evaluation

language models

technical paper

Welcome to the 18th 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 has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. 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. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

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.

Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages. The key challenge is that, due to high morphological complexity and ambiguity of the space-delimited input tokens, the linguistic units that act as nodes in the tree are not known in advance. Pre-neural dependency parsers for MRLs subscribed to the {\em joint morpho-syntactic hypothesis}, stating that morphological segmentation and syntactic parsing should be solved jointly, rather than as a pipeline where segmentation precedes parsing. However, neural state-of-the-art parsers to date use a strict pipeline. 
In this paper we introduce a joint neural architecture where a lattice-based representation preserving all morphological ambiguity of the input is provided to an arc-factored model, which then solves the morphological segmentation and syntactic parsing tasks at once. Our experiments on Hebrew, a rich and highly ambiguous MRL, demonstrate state-of-the-art performance on parsing, tagging and segmentation of the Hebrew section of UD, using a single model. This proposed architecture is LLM-based and language agnostic, providing a solid foundation for MRLs to obtain further performance improvements and bridge the gap with other languages.

A Truly Joint Neural Architecture for Segmentation and Parsing

Graph-based semantic representations are popular in natural language processing (NLP), where it is often convenient to model linguistic concepts as nodes and relations as edges between them. Several attempts have been made to find a generative device that is sufficiently powerful to describe languages of semantic graphs, while at the same allowing efficient parsing. We contribute to this line of work by introducing graph extension grammar, a variant of the contextual hyperedge replacement grammars proposed by Hoffmann et al. Contextual hyperedge replacement can generate graphs with non-structural reentrancies, a type of node-sharing that is very common in formalisms such as abstract meaning representation, but which context-free types of graph grammars cannot model. To provide our formalism with a way to place reentrancies in a linguistically meaningful way, we endow rules with logical formulas in counting monadic second-order logic. We then present a parsing algorithm and show as our main result that this algorithm runs in polynomial time on graph languages generated by a subclass of our grammars, the so-called local graph extension grammars.

Generation and Polynomial Parsing of Graph Languages with Non-Structural Reentrancies

Acoustic word embeddings (AWEs) are vector representations of spoken words. An effective method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the CAE method has been associated with traditional MFCC features. Representations obtained from self-supervised learning (SSL)-based speech models such as HuBERT, Wav2vec2, etc., are outperforming MFCC in many downstream tasks. However, they have not been well studied in the context of learning AWEs. This work explores the effectiveness of CAE with SSL-based speech representations to obtain improved AWEs. Additionally, the capabilities of SSL-based speech models are explored in cross-lingual scenarios for obtaining AWEs. Experiments are conducted on five languages: Polish, Portuguese, Spanish, French, and English. HuBERT-based CAE model achieves the best results for word discrimination in all languages, despite HuBERT being pre-trained on English only. Also, the HuBERT-based CAE model works well in cross-lingual settings. It outperforms MFCC-based CAE models trained on the target languages when trained on one source language and tested on target languages.

Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations

We present a new Hindi text-to-speech (TTS) dataset and demonstrate its utility for the expressive synthesis of children's audio stories. The dataset comprises narration by a single female speaker who modifies her voice to produce different story characters. Annotation for dialogue identification, character labelling, and character attribution are provided, all of which are expected to facilitate the learning of character voice and speaking styles. Experiments are conducted using different versions of the annotated dataset that enable training a multi-speaker TTS model on the single-speaker data. Subjective tests show that the multi-speaker model improves expressiveness and character voice consistency compared to the baseline single-speaker TTS. With the multi-speaker model, objective evaluations show comparable word error rates, better speaker voice consistency, and higher correlations with ground-truth emotion attributes. We release a new 16.8 hours storytelling speech dataset in Hindi and propose effective solutions for expressive TTS with narrator voice modulation and character voice consistency.

STORiCo: Storytelling TTS for Hindi with Character Voice Modulation

Much texts describe a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crowdsourced annotations of entity state changes in text. However, a major limitation was that those annotations were free-form and did not identify salient changes, hampering model evaluation. To overcome these limitations, we present an improved dataset, OpenPI2.0, where entities and attributes are fully canonicalized and additional entity salience annotations are added. On our fairer evaluation setting, we find that current state-of-the-art language models are far from competent. We also show that using state changes of salient entities as a chain-of-thought prompt, downstream performance is improved on tasks such as question answering and classical planning, outperforming the setting involving all related entities indiscriminately. We offer OpenPI2.0 for the continued development of models that can understand the dynamics of entities in text.

OpenPI2.0: An Improved Dataset for Entity Tracking in Texts

Over 15 years ago, Ward & Birner (2006) suggested that non-canonical constructions in English can serve both to mark information status and to structure the information flow of discourse. One such construction is preposing, where a phrasal constituent appears to the left of its canonical position, typically sentence-initially. But computational work on discourse has, to date, ignored non-canonical syntax. We take account of non-canonical syntax by providing quantitative evidence relating NP/PP preposing to discourse relations. The evidence comes from an LLM mask-filling task that compares the predictions when a mask is inserted between the arguments of an implicit inter-sentential discourse relation --- first, when the right-hand argument (Arg2) starts with a preposed constituent, and again, when that constituent is in canonical (post-verbal) position. Results show that (1) the top-ranked mask-fillers in the preposed case agree more often with "gold" annotations in the Penn Discourse TreeBank than they do in the latter case, and (2) preposing in Arg2 can affect the distribution of discourse-relational senses.

Syntactic Preposing and Discourse Relations

Emotion recognition in conversation (ERC) has attracted much attention due to its wide applications. While consistent improvement is being made in this area, inevitable challenge comes from the dataset. The ERC dataset exhibits significantly imbalanced emotion distribution. While the utterances with neutral emotion predominate the data, this emotion label is always treated the same as other emotion labels in current approaches. To address the problem caused by the dataset, we propose a supervised contrastive learning specifically oriented for ERC task. We employ a novel data augmentation method emulating the emotion dynamics in a conversation and formulate supervised contrastive learning method tailored for ERC addressing the predominance and the ambiguity of neutral emotion. Experimental results on four benchmark datasets demonstrate the effectiveness of our approach.

Improving Contrastive Learning in Emotion Recognition in Conversation via Data Augmentation and Decoupled Neutral Emotion

The representation degeneration problem is a phenomenon that is widely observed among self-supervised learning methods based on Transformers. In NLP, it takes the form of anisotropy, a singular property of hidden representations which makes them unexpectedly close to each other in terms of angular distance (cosine-similarity). Some recent works tend to show that anisotropy is a consequence of optimizing the cross-entropy loss on long-tailed distributions of tokens. We show in this paper that anisotropy can also be observed empirically in language models with specific objectives that should not suffer directly from the same consequences. We also show that the anisotropy problem extends to Transformers trained on other modalities. Our observations tend to demonstrate that anisotropy might actually be inherent to Transformers-based models.

Anisotropy Is Inherent to Self-Attention in Transformers

The differences between cloze-task language model (LM) probing with 1) expert-made templates and 2) naturally-occurring text have often been overlooked. Here, we evaluate 16 different LMs on 10 probing English datasets – 4 template-based and 6 template-free – in general and biomedical domains to answer the following research questions: (RQ1) Do model rankings differ between the two approaches? (RQ2) Do models’ absolute scores differ between the two approaches? (RQ3) Do the answers to RQ1 and RQ2 differ between general and domain-specific models? Our findings are: 1) Template-free and template-based approaches often rank models differently, except for the top domain- specific models. 2) Scores decrease by up to 42% Acc@1 when comparing parallel template-free and template-based prompts. 3) Perplexity is negatively correlated with accuracy in the template-free approach, but, counter-intuitively, they are positively correlated for template-based probing. 4) Models tend to predict the same answers frequently across prompts for template-based probing, which is less common when employing template-free techniques.

Comparing Template-based and Template-free Language Model Probing

In recent years, large language models (LLMs) have become increasingly prevalent, offering remarkable text generation capabilities. However, a pressing challenge is their tendency to make confidently wrong predictions, highlighting the critical need for uncertainty quantification (UQ) in LLMs. While previous works have mainly focused on addressing aleatoric uncertainty, the full spectrum of uncertainties, including epistemic, remains inadequately explored. Motivated by this gap, we introduce a novel UQ method, sampling with perturbation for UQ (SPUQ), designed to tackle both aleatoric and epistemic uncertainties. The method entails generating a set of perturbations for LLM inputs, sampling outputs for each perturbation, and incorporating an aggregation module that generalizes the sampling uncertainty approach for text generation tasks. Through extensive experiments on various datasets, we investigated different perturbation and aggregation techniques. Our findings show a substantial improvement in model uncertainty calibration, with a reduction in Expected Calibration Error (ECE) by 50% on average. Our findings suggest that our proposed UQ method offers promising steps toward enhancing the reliability and trustworthiness of LLMs.

Anchor Points: Benchmarking Models with Much Fewer Examples

Downloads

Next from EACL 2024

A Truly Joint Neural Architecture for Segmentation and Parsing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Anchor Points: Benchmarking Models with Much Fewer Examples

.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 EACL 2024

A Truly Joint Neural Architecture for Segmentation and Parsing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads