Keyphrase extraction

Overview

Keyphrase extraction selects the words or short phrases that best describe a text. The one card so far frames it as sequence labelling: each token is tagged with B, I, E, S or O, and the selected tokens form the keyphrases 2606.26485 §3.2. The hard case is short, noisy text such as tweets, where context is thin and hashtags are often missing 2606.26485 §1. Evaluation is top-k keyphrase precision, recall and F1 2606.26485 §4.1.

The variant covered here adds per-word human reading signals (eye tracking and EEG from the ZuCo corpus) to neural taggers 2606.26485 §3.1, §3.2. The sections below describe the tagger families it tests, with the reading-signal features as an add-on to each. Card: Cognitive signals for keyphrase extraction from microblogs.

Variants

Bi-LSTM taggers

The baseline is a Bi-LSTM, and a Bi-LSTM with a CRF output layer. The cognitive vector is concatenated to the word embedding before the Bi-LSTM 2606.26485 §3.2.1. Results: on Election-Trec the Bi-LSTM baseline scores 61.67 F1, and on General-Twitter 70.67 F1 2606.26485 tab. 4, §4.2. Card: Cognitive signals for keyphrase extraction from microblogs.

Soft-attention taggers

A learned attention vector scores the Bi-LSTM states and their weighted combination feeds the output. The paper adds the cognitive vector to the attention input 2606.26485 §3.2.2. The card notes that the released code places the features elsewhere, so the description here follows the paper only. Card: Cognitive signals for keyphrase extraction from microblogs.

Self-attention taggers

Self-attention layers, with or without a CRF, are tested with the cognitive vector appended to the query 2606.26485 §3.2.2. This is the best setting in the paper: SATT-BiLSTM+CRF with EEG reaches 67.82 F1 on Election-Trec and 82.46 F1 on General-Twitter 2606.26485 tab. 4, §4.2. The released code for this model does not run as written, according to the card's Paper vs code section. Card: Cognitive signals for keyphrase extraction from microblogs.

Pre-trained encoders

The paper also tests GloVe embeddings in the self-attention tagger, BERT with a linear tagging head, and T5-Base and T5-Large with a linear head 2606.26485 §3.2.3. Gains from the reading signals are small here: T5-Large moves from 75.10 to 76.99 F1 on Election-Trec, and BERT from 71.79 to 71.82 2606.26485 tab. 7, §4.5. Card: Cognitive signals for keyphrase extraction from microblogs.

When to use which

Only one card is available, so these rows compare settings inside that paper. They are not a survey of keyphrase extraction.

Implementation sketch

The common core is a token tagger with an optional per-word feature vector. The variants differ in where the vector enters (the paper's choices are described in each variant above).

# Keyphrase tagger with optional per-word features  [arxiv:2606.26485 §3.2]
# Input:  word_ids (B, L); feats (B, L, k) or None; mask (B, L)
# Output: tag scores (B, L, 5) for B, I, E, S, O

def keyphrase_tagger(word_ids, feats, mask):
    # Look up word embeddings  [arxiv:2606.26485 §3.2.1]
    embedded = embedding(word_ids)                  # (B, L, d)
    # Concatenate the per-word feature vector before encoding  [§3.2.1]
    if feats is not None:
        embedded = concat(embedded, feats)          # (B, L, d + k)
    # Encode the sequence with a Bi-LSTM  [§3.2.1]
    hidden = bilstm(embedded)                       # (B, L, 2h)
    # Optional attention layer; placement depends on variant  [§3.2.2]
    hidden = maybe_attention(hidden, feats, mask)
    # Score each token; CRF decoding is an option  [§3.2.1]
    return linear(hidden)                           # (B, L, 5)

Contradictions

None known between papers, since only one card exists. The paper and its released code disagree on several points, including which EEG features are used, where features enter the attention models, and the pooling in soft attention. These are listed on the card's Paper vs code section, and they affect whether the reported numbers can be reproduced. See Cognitive signals for keyphrase extraction from microblogs.

Papers

• Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs: adds per-word EEG and eye-tracking features to Bi-LSTM and attention taggers for tweets; author-reported best F1 is 67.82 (Election-Trec) and 82.46 (General-Twitter) 2606.26485 tab. 4.