# Input pattern file to terms.teach

**URL:** <https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382>\
**Category:** Uncategorized\
**Created:** [February 23, 2023, 1:52am UTC](https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382 "2023-02-23T01:52:44Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![jsnleong](https://avatars.discourse-cdn.com/v4/letter/j/b9bd4f/32.png) [@jsnleong](https://support.prodi.gy/u/jsnleong)\
**Post date:** [February 23, 2023, 1:52am UTC](https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382/1 "2023-02-23T01:52:44Z")

</div>

Hi guys!

Is it possible to add pattern files as an argument to terms.teach recipe? Used to see this being available in older versions of Prodigy, but don't see it anymore in current documentation.

I think the patterns would be useful to kickstart and narrow the search space.

Thanks! Jason

---

<div class="post-metadata">

**Author:** ![koaning](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/koaning/32/230_2.png) [@koaning](https://support.prodi.gy/u/koaning)\
**Post date:** [February 23, 2023, 9:11am UTC](https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382/2 "2023-02-23T09:11:15Z")

</div>

Hi Jason.

Do you remember the Prodigy version from before? I checked the changelog but couldn't find the change there.

That said, if you check the [terms.teach recipe](https://prodi.gy/docs/recipes#terms-teach) you should see a `--seeds` option that allows you to pass in strings but also a file with one term per line. Does this suffice? I can imagine that we don't support general patterns here because the `terms.teach` recipe assumes single token terms, while patterns could have multiple tokens.

---

<div class="post-metadata">

**Author:** ![jsnleong](https://avatars.discourse-cdn.com/v4/letter/j/b9bd4f/32.png) [@jsnleong](https://support.prodi.gy/u/jsnleong)\
**Post date:** [February 24, 2023, 1:26am UTC](https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382/3 "2023-02-24T01:26:46Z")

</div>

Hi koaning,

Actually one token doesn't suffice. Would like to have multiple patterns generated from terms.teach as a pattern file for text classification.

Understand that we can use Sense2vec instead, however, the vector dictionary can I still use spacy's one? I am training Chinese text, so am using zh\_core\_web\_lg, but encountered issues running.

Thanks!

---

<div class="post-metadata">

**Author:** ![koaning](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/koaning/32/230_2.png) [@koaning](https://support.prodi.gy/u/koaning)\
**Post date:** [February 24, 2023, 10:31am UTC](https://support.prodi.gy/t/input-pattern-file-to-terms-teach/6382/4 "2023-02-24T10:31:49Z")

</div>

The idea behind the `sense2vec` trick might work, but unfortunately the current pre-trained model only provides support for English.

I'm about to propose another trick that _might_ work, but I want to be careful that I don't over-promise anything since I don't speak Chinese. But one thing that you might do is create a spaCy script that can fetch "chunks of tokens that might form a noun". For English, this is supported directly via `Doc.noun_chunks` but I believe this [isn't supported for Chinese](https://github.com/explosion/spaCy/issues/7436). You might, however, try to construct something similar by hand.

Here's how I might construct it for English using `noun_chunks`.

```python
import spacy 

nlp = spacy.load("en_core_web_md")

doc = nlp("Pepperoni pizzas are an amazing Italian dish.")
for chunk in doc.noun_chunks:
    print(chunk)

# Pepperoni pizzas
# an amazing Italian dish

```

Here's another way of doing something similar without using the `.noun_chunks` property.

```python
from spacy import displacy 

displacy.render(doc)

```

We could find chunks manually by looking for `noun` tokens that are a "root". That is to say, we're looking for nouns have that children in the dependency graph.

 ![CleanShot 2023-02-24 at 11.00.02](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/8/875b68c89dd8b18c1215fc77f3a534edc7eaa25c.png)

Here's a little script that can do that.

```python
for tok in doc:
    if tok.pos_ == "NOUN":
        children = list(tok.children)
        if children:
            token_idx = [tok.i] + [t.i for t in children]
            print(doc[min(token_idx): max(token_idx) + 1])
# Pepperoni pizzas
# an amazing Italian dish

```

There are variants of this script you might consider, but this is _a_ way to fetch multi-token chunks from your corpus. And _this_ might also work for Chinese.

Here's an example I made using Google translate.

```python
import spacy

nlp = spacy.load("zh_core_web_sm")
doc = nlp("意大利辣香肠比萨饼是一道很棒的意大利菜")

for tok in doc:
    if tok.pos_ == "NOUN":
        children = list(tok.children)
        if children:
            token_idx = [tok.i] + [t.i for t in children]
            print(doc[min(token_idx): max(token_idx) + 1])
# 意大利辣香肠
# 是一道很棒的意大利菜

```

From here, you might even be able to construct phrases with vectors from the spaCy pipeline.

```python
import spacy

nlp = spacy.load("zh_core_web_sm")
doc = nlp("意大利辣香肠比萨饼是一道很棒的意大利菜")

phrases = {}
for tok in doc:
    if tok.pos_ == "NOUN":
        children = list(tok.children)
        if children:
            token_idx = [tok.i] + [t.i for t in children]
            phrase = doc[min(token_idx): max(token_idx) + 1]
            phrases[phrase.text] = phrase.vector[:5]

```

This will give a dictionary, `phrases`, that maps phrase texts to vectors.

```python
{
   '意大利辣香肠': array([-0.217975 , -1.4146296 , 1.3613806 , -0.09676328, -0.1946054, ...],dtype=float32),
   '是一道很棒的意大利菜': array([-0.19973822, 0.54612845, 0.09049363, -0.17543283, 0.31415954, ...], dtype=float32)
}

```

These vectors can then be used to find phrases that are similar. This would involve custom code, but might be worth a try.

Again, I really want to stress that I cannot judge if this will work for Chinese, and a lot of the utility will depend on the spaCy pipeline. But I'm mentioning it because the exercise does seem to be worth a try. Could you let me know if this direction does/not work for you? I am very much interested in hearing your reply!