Thailand

Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identify-then-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/PA-CRF.

IJCNLP-AACL 2021

{F}ew-{S}hot {E}vent {D}etection with {P}rototypical {A}mortized {C}onditional {R}andom {F}ield

event detection

few-shot learning

meta-learning

**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

This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 social media data. 
We develop guidelines to conduct a controlled annotation study with social science students and find that suggestions from a model trained on a small, expert-annotated dataset already lead to a substantial improvement – in terms of inter-annotator agreement (+.14 Fleiss’ κ) and annotation quality – compared to students that do not receive any label suggestions. 
We further find that label suggestions from interactively trained models do not lead to an improvement over suggestions from a static model. 
Nonetheless, our analysis of suggestion bias shows that annotators remain capable of reflecting upon the suggested label in general. 
Finally, we confirm the quality of the annotated data in transfer learning experiments between different annotator groups. 
To facilitate further research in opinion mining on social media data, we release our collected data consisting of 200 expert and 2,785 student annotations.

Investigating label suggestions for opinion mining in German Covid-19 social media

Humor is an important social phenomenon, serving complex social and psychological functions. However, despite being studied for millennia humor is computationally not well understood, often considered an AI-complete problem.
In this work, we introduce a novel setting in humor mining: automatically detecting funny and unusual scientific papers. We are inspired by the Ig Nobel prize, a satirical prize awarded annually to celebrate funny scientific achievements (example past winner: “Are cows more likely to lie down the longer they stand?”). This challenging task has unique characteristics that make it particularly suitable for automatic learning.
We construct a dataset containing thousands of funny papers and use it to learn classifiers, combining findings from psychology and linguistics with recent advances in NLP. We use our models to identify potentially funny papers in a large dataset of over 630,000 articles. The results demonstrate the potential of our methods, and more broadly the utility of integrating state-of-the-art NLP methods with insights from more traditional disciplines

How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements

We propose an explainable inference approach for science questions by reasoning on grounding and abstract inference chains. This paper frames question answering as a natural language abductive reasoning problem, constructing plausible explanations for each candidate answer and then selecting the candidate with the best explanation as the final answer. Our method, ExplanationLP, elicits explanations by constructing a weighted graph of relevant facts for each candidate answer and employ a linear programming formalism designed to select the optimal subgraph of explanatory facts. The graphs' weighting function is composed of a set of parameters targeting relevance, cohesion and diversity, which we fine-tune for answer selection via Bayesian Optimisation. We carry out our experiments on the WorldTree and ARC-Challenge datasets to empirically demonstrate the following contributions: (1) ExplanationLP obtains strong performance when compared to transformer-based and multi-hop approaches despite having a significantly lower number of parameters (2) We illustrate that our model is able to generate plausible explanations for answer prediction
(3) Our model demonstrates better robustness towards semantic drift when compared to transformer-based and multi-hop approaches

Explainable Inference Over Grounding-Abstract Chains for Science Questions

Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order. Specifically, besides the original self-attention and feed-forward layers, we introduce convolution into the layer type set, which is experimentally found beneficial to pre-trained models. Furthermore, beyond the original interleaved order, we explore more layer orders to discover more powerful architectures. However, the introduced layer variety leads to a large architecture space of more than billions of candidates, while training a single candidate model from scratch already requires huge computation cost, making it not affordable to search such a space by directly training large amounts of candidate models. To solve this problem, we first pre-train a supernet from which the weights of all candidate models can be inherited, and then adopt an evolutionary algorithm guided by pre-training accuracy to find the optimal architecture. Extensive experiments show that LV-BERT model obtained by our method outperforms BERT and its variants on various downstream tasks. For example, LV-BERT-small achieves 78.8 on the GLUE testing set, 1.8 higher than the strong baseline ELECTRA-small.

LV-BERT: Exploiting Layer Variety for BERT

Report on the journal

This is an incredible moment for NLP. We all routinely work with models whose capabilities would have seemed like science fiction just two decades ago, powerful organizations eagerly await our latest results, and NLP technologies are playing an increasingly large role in shaping our society. As a result, all of us in the NLP community are likely to participate in research that will contribute (to varying degrees and perhaps only indirectly) to technologies that will impact many people’s lives, with both positive and negative consequences for example, technologies that broaden accessibility, enhance creative self-expression, heighten surveillance, and create propaganda. What can we do to fulfill the social responsibility that this brings? As a (very) partial answer to this question, I will review a number of important recent developments, spanning many research groups, concerning dataset creation, model introspection, and system assessment. Taken together, these ideas can help us more reliably characterize how NLP systems will behave, and more reliably communicate this information to a wider range of potential users. In this way, they can help us meet our obligations to the people whose lives are impacted by the results of our research.

{F}ew-{S}hot {E}vent {D}etection with {P}rototypical {A}mortized {C}onditional {R}andom {F}ield

Downloads

Next from IJCNLP-AACL 2021

Investigating label suggestions for opinion mining in German Covid-19 social media

Similar lecture

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

{F}ew-{S}hot {E}vent {D}etection with {P}rototypical {A}mortized {C}onditional {R}andom {F}ield

.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

Investigating label suggestions for opinion mining in German Covid-19 social media

Similar lecture

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

Downloads