Thailand

Evaluation in NLP is usually done by comparing the scores of competing systems independently averaged over a common set of test instances.
In this work, we question the use of averages for aggregating evaluation scores into a final number used to decide which system is best, since the average, as well as alternatives such as the median, ignores the pairing arising from the fact that systems are evaluated on the same test instances.
We illustrate the importance of taking the instance\hyp level pairing of evaluation scores into account and demonstrate, both theoretically and empirically, the advantages of aggregation methods based on pairwise comparisons, such as the Bradley--Terry (BT) model, a mechanism based on the estimated probability that a given system scores better than another on the test set. By re-evaluating 296 real NLP evaluation setups across four tasks and 18 evaluation metrics, we show that the choice of aggregation mechanism matters and yields different conclusions as to which systems are state of the art in about 30% of the setups.
To facilitate the adoption of pairwise evaluation, we release a practical tool for performing the full analysis of evaluation scores with the mean, median, BT, and two variants of BT (Elo and TrueSkill), alongside functionality for appropriate statistical testing.

IJCNLP-AACL 2021

Better than Average: Paired Evaluation of NLP systems

median

mean

paired

aggregation

evaluation

**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).

technical paper

Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER, we encode textual entity descriptions with a PLM as their embeddings, and then jointly optimize the KE and language modeling objectives. Experimental results show that KEPLER achieves state-of-the-art performances on various NLP tasks, and also works remarkably well as an inductive KE model on KG link prediction. Furthermore, for pretraining and evaluating KEPLER, we construct Wikidata5M, a large-scale KG dataset with aligned entity descriptions, and benchmark state-of-the-art KE methods on it. It shall serve as a new KE benchmark and facilitate the research on large KG, inductive KE, and KG with text. The source code can be obtained from https://github.com/THU-KEG/KEPLER.

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale information retrieval. To generate high-quality hashing code, both semantics and neighborhood information are crucial. However, most existing methods leverage only one of them or simply combine them via some intuitive criteria, lacking a theoretical principle to guide the integration process. In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. To deal with the complicated correlations among documents, we further propose a tree-structured approximation method for learning. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones. Extensive experimental results on three benchmark datasets show that our method achieves superior performance over state-of-the-art methods, demonstrating the effectiveness of the proposed model for simultaneously preserving semantic and neighborhood information.

Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval

Imagine you are in a supermarket. You have two bananas in your basket and want to buy four apples. How many fruits do you have in total? This seemingly straightforward question can be challenging for data-driven language models, even if trained at scale. However, we would expect such generic language models to possess some mathematical abilities in addition to typical linguistic competence. 

Towards this goal, we investigate if a commonly used language model, BERT, possesses such mathematical abilities and, if so, to what degree. For that, we fine-tune BERT on a popular dataset for word math problems, AQuA-RAT, and conduct several tests to understand learned representations better.

Since we teach models trained on natural language to do formal mathematics, we hypothesize that such models would benefit from training on semi-formal steps that explain how math results are derived. To better accommodate such training, we also propose new pretext tasks for learning mathematical rules. We call them (Neighbor) Reasoning Order Prediction (ROP or NROP). With this new model, we achieve significantly better outcomes than data-driven baselines and even on-par with more tailored models.

Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning.

The open-ended nature of visual captioning makes it a challenging area for evaluation. The majority of proposed models rely on specialized training to improve human-correlation, resulting in limited adoption, generalizability, and explainabilty. We introduce "typicality", a new formulation of evaluation rooted in information theory, which is uniquely suited for problems lacking a definite ground truth. Typicality serves as our framework to develop a novel semantic comparison, SPARCS, as well as referenceless fluency evaluation metrics. Over the course of our analysis, two separate dimensions of fluency naturally emerge: style, captured by metric SPURTS, and grammar, captured in the form of grammatical outlier penalties. Through extensive experiments and ablation studies on benchmark datasets, we show how these decomposed dimensions of semantics and fluency provide greater system-level insight into captioner differences. Our proposed metrics along with their combination, SMURF, achieve state-of-the-art correlation with human judgment when compared with other rule-based evaluation metrics.

SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis

The goal of database question answering is to enable natural language querying of real-life relational databases in diverse application domains. Recently, large-scale datasets such as Spider and WikiSQL facilitated novel modeling techniques for text-to-SQL parsing, improving zero-shot generalization to unseen databases. In this work, we examine the challenges that still prevent these techniques from practical deployment. First, we present KaggleDBQA, a new cross-domain evaluation dataset of real Web databases, with domain-specific data types, original formatting, and unrestricted questions. Second, we re-examine the choice of evaluation tasks for text-to-SQL parsers as applied in real-life settings. Finally, we augment our in-domain evaluation task with database documentation, a naturally occurring source of implicit domain knowledge. We show that KaggleDBQA presents a challenge to state-of-the-art zero-shot parsers but a more realistic evaluation setting and creative use of associated database documentation boosts their accuracy by over 13.2%, doubling their performance.

KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers

We introduce the largest transcribed Arabic speech corpus, QASR, collected from the broadcast domain. This multi-dialect speech dataset contains 2,000 hours of speech sampled at 16kHz crawled from Aljazeera news channel. The dataset is released with lightly supervised transcriptions, aligned with the audio segments. Unlike previous datasets, QASR contains linguistically motivated segmentation, punctuation, speaker information among others. QASR is suitable for training and evaluating speech recognition systems, acoustics- and/or linguistics- based Arabic dialect identification, punctuation restoration, speaker identification, speaker linking, and potentially other NLP modules for spoken data. 
In addition to QASR transcription, we release a dataset of 130M words to aid in designing and training a better language model. We show that end-to-end automatic speech recognition trained on QASR reports a competitive word error rate compared to the previous MGB-2 corpus. We report baseline results for downstream natural language processing tasks such as named entity recognition using speech transcript. We also report the first baseline for Arabic punctuation restoration. We make the corpus available for the research community.

QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus

The performance of fine-tuning pre-trained language models largely depends on the hyperparameter configuration. 
In this paper, we investigate the performance of modern hyperparameter optimization methods (HPO) on fine-tuning pre-trained language models. 
First, we study and report three HPO algorithms' performances on fine-tuning two state-of-the-art language models on the GLUE dataset. We find that using the same time budget, HPO often fails to outperform grid search due to two reasons: insufficient time budget and overfitting. We propose two general strategies and an experimental procedure to systematically troubleshoot HPO's failure cases. By applying the procedure, we observe that HPO can succeed with more appropriate settings in the search space and time budget; however, in certain cases overfitting remains. Finally, we make suggestions for future work. Our implementation can be found in \url{https://github.com/microsoft/FLAML/tree/main/flaml/nlp/}

An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models

The current paradigm of applying a pre-trained language model to a downstream task is to finetune it on labeled task data, which often suffers instability and low performance when the labeled examples are scarce. One way to alleviate this problem is to apply post-training on unlabeled task data before the fine-tuning, and adapt the pre-trained model to the task domain by contrastive learning which considers either token-level or sequence-level similarity. Inspired by the success in sequence masking, we argue that both token-level and sequence-level similarities can be captured with a pair of masked sequences. Therefore, we develop complementary random masking (CRM) to generate a pair of masked sequences from an input sequence for sequence-level contrastive learning, and propose contrastive masked language modeling (CMLM) for post-training to integrate both token-level and sequence-level contrastive learnings. Empirical results show that CMLM surpasses several recent posttraining methods in few-shot settings without the need for data augmentation as they do.

Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene

A comprehensive knowledge graph (KG) contains an instance-level entity graph and an ontology-level concept graph. The two-view KG provides a testbed for models to "simulate" human's abilities on knowledge abstraction, concretization, and completion (KACC), which are crucial for human to recognize the world and manage learned knowledge. Existing studies mainly focus on partial aspects of KACC. In order to promote thorough analyses for KACC abilities of models, we propose a unified KG benchmark by improving existing benchmarks in terms of dataset scale, task coverage, and difficulty. Specifically, we collect new datasets that contain larger concept graphs, abundant cross-view links as well as dense entity graphs. Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark. For MKA and MKC tasks, we further annotate multi-hop hierarchical triples as harder samples. The experimental results of existing methods demonstrate the challenges of our benchmark. The resource is available at https://github.com/thunlp/KACC.

KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion

Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, including political science, digital humanities and sociological research in general. One desirable property of topic models is to allow users to find topics describing a specific aspect of the corpus. A possible solution is to incorporate domain-specific knowledge into topic modeling, but this requires a specification from domain experts. We propose a novel query-driven topic model that allows users to specify a simple query in words or phrases and return query-related topics, thus avoiding tedious work from domain experts. Our proposed approach is particularly attractive when the user-specified query has a low occurrence in a text corpus, making it difficult for traditional topic models built on word cooccurrence patterns to identify relevant topics. Experimental results demonstrate the effectiveness of our model in comparison with both classical topic models and neural topic models.

Better than Average: Paired Evaluation of NLP systems

Downloads

Next from IJCNLP-AACL 2021

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

Similar lecture

HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Better than Average: Paired Evaluation of NLP systems

.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 IJCNLP-AACL 2021

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

Similar lecture

HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads