Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media

Abstract

Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-toend Bidirectional Long Short-Term Memory (BLSTM)-Conditional Random Field (CRF) network whose output layer contains two CRF classifiers. The second model uses a multitask BLSTM network as feature extractor that transfers the learning to a CRF classifier for the final prediction. Our systems outperform the current F1 scores of the state of the art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments.

Pooled Contextualized Embeddings for Named Entity Recognition

“…has not yet experimented with contextual embeddings on WNUT, as side result we report a new state-of-the-art of 49.59 F1 vs. the previous best reported number of 45.55 (Aguilar et al, 2018).…”

“…This result is expected since most entities appear only few times in this dataset, giving our approach little evidence to aggregate and pool. Nevertheless, since recent work has not yet experimented with contextual embeddings on WNUT, as side result we report a new state-of-the-art of 49.59 F1 vs. the previous best reported number of 45.55 (Aguilar et al, 2018). Pooling operations.…”

“…In addition, we list the best reported numbers for the four tasks. This includes the recent BERT approach using bidirectional transformers by Devlin et al (2018), the semi-supervised multitask learning approach by , the ELMo word-level language modeling approach by Peters et al (2018), and the best published numbers for WNUT-17 (Aguilar et al, 2018) and German and Dutch CONLL-03 (Lample et al, 2016).…”

Learning Architectures from an Extended Search Space for Language Modeling

“…After architecture search, we test the transferability of the learned architecture. In order to apply the model to other tasks, we directly use the architecture searched on WikiText-103 and train the param-Models F1 Cross-BiLSTM-CNN (Aguilar et al, 2018) (Yang and Zhang, 2018) 95.06 BiLSTM-CRF + IntNet (Xin et al, 2018) 95.29 Flair (Akbik et al, 2019) 96.72 GCDT + BERTLARGE (Liu et al, 2019b) 97 eters with the in-domain data. In our experiments, we adapt the model to CoNLL-2003, WNUT-2017NER tasks and CoNLL-2000 For the two NER tasks, it achieves new stateof-the-art F1 scores (Table 4 and Table 5).…”

Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing

“…and Rei (2017) studied multi-task learning of sequence labeling with language models. Aguilar et al (2018) and Cao et al (2018) proposed multi-task learning of NER with word segmentation. Peng and Dredze (2017)'s method of multi-task learning leverages the performance of domain adaptation.…”